Aspire Journeys

# ML Programmer to ML Architect

- 76 Courses | 71h 49m 43s
- 4 Labs | 30h
- Includes Test Prep

Machine Learning Architects interpret real-time analysis of data to automate and increase efficiency across all business domains, setting the stage for meaningful AI that moves from reactive to predictive. This Skillsoft Aspire journey will guide you in the transition from becoming a DL Programmer to a ML/DL Architect Master through mechanisms such as computational theory.

**Track 1: ML Programmer**

In this track of the machine learning Skillsoft Aspire journey, the focus is linear regression, computational theory, and training sets.

- 25 Courses | 21h 55m 15s
- 1 Lab | 8h

**Track 2: DL Programmer**

In this track of the machine learning Skillsoft Aspire journey, the focus is neural networks, CNNs, RNNs, and ML algorithms.

- 22 Courses | 21h 19m 49s
- 1 Lab | 8h

**Track 3: ML Engineer**

In this track of the machine learning Skillsoft Aspire journey, the focus is predictive modeling and analytics, ml modeling, and ml architecting.

- 17 Courses | 16h 13m 15s
- 1 Lab | 8h

**Track 4: ML Architect**

In this track of the machine learning Skillsoft Aspire journey, the focus is applied predictive modeling, CNNs and RNNs, and ML algorithms.

- 12 Courses | 12h 21m 24s
- 1 Lab | 6h

**COURSES INCLUDED**

**NLP for ML with Python: NLP Using Python & NLTK**

This course explores how natural language processing (NLP) is used for machine learning, and examines the benefits and challenges of NLP when creating an application that can essentially understand human language. In its 13 videos, learners will be shown the essential components of NLP, including parsers, corpus, and corpus linguistic, as well as how to implement regular expressions. This course goes on to examine tokenization, a way to separate a piece of text into smaller units, and then illustrates different tokenization use cases with NLTK (Natural Language Toolkit). You will learn to use stop words using libraries and the NLTK. This course demonstrates how to implement regular expressions in Python to build NLP-powered applications. Learners will examine the list of Python NLP libraries along with their essential capabilities, including NLTK, Gensim, CoreNLP, spaCy and PyNLPl. You will learn to set up and configure an NLTK environment to illustrate how to process raw text. Finally, this course demonstrates the use of filtering stopwords in a tokenized sentence using NLTK.

13 videos |
1h 1m
Assessment
Badge
**NLP for ML with Python: Advanced NLP Using spaCy & Scikit-learn**

This 11-video course explores NLP (natural language processing) by discussing differences between stemming, a process of reducing a word to its word stem, and lemmatization, or returning the base or dictionary form of a word. Key concepts covered here include how to extract synonyms, antonyms, and topic, and how to process and analyze texts for machine learning. You will learn to use Apache's Natural Language Toolkit (NLTK), spaCy, and Scikit-learn to implement text classification and sentiment analysis. This course demonstrates the use of advanced calculus and discrete optimization to implement robust and high-performance machine learning applications. You will learn to use R and Python to implement multivariate calculus for machine learning and data science, then examine the role of probability, variance, and random vectors in implementing machine learning processes and algorithms. Finally, you will examine the role of calculus in deep learning; watch a demonstration of how to apply calculus and differentiation using R and Python libraries; see how to implement calculus, derivatives, and integrals using Python; and learn uses of limits and series expansions in Python.

11 videos |
40m
Assessment
Badge
**Linear Algebra and Probability: Fundamentals of Linear Algebra**

Explore the fundamentals of linear algebra, including characteristics and its role in machine learning, in this 13-video course. Learners can examine important concepts associated with linear algebra, such as the class of spaces, types of vector space, vector norms, linear product vector and theorems, and various operations that can be performed on matrix. Key concepts examined in this course include important classes of spaces associated with linear algebra; features of vector spaces and the different types of vector spaces and their application in distribution and Fourier analysis; and inner product spaces and the various theorems that are applied on inner product spaces. Next, you will learn how to implement vector arithmetic by using Python; learn how to implement vector scalar multiplication with Python; and learn the concept and different types of vector norms. Finally, learn how to implement matrix-matrix multiplication, matrix-vector multiplication, and matric-scalar multiplication by using Python; and learn about matrix decomposition and the roles of Eigenvectors and Eigenvalues in machine learning.

13 videos |
1h 40m
Assessment
Badge
**Linear Algebra & Probability: Advanced Linear Algebra**

Learners will discover how to apply advanced linear algebra and its principles to derive machine learning implementations in this 14-video course. Explore PCA, tensors, decomposition, and singular-value decomposition, as well as how to reconstruct a rectangular matrix from singular-value decomposition. Key concepts covered here include how to use Python libraries to implement principal component analysis with matrix multiplication; sparse matrix and its operations; tensors in linear algebra and arithmetic operations that can be applied; and how to implement Hadamard product on tensors by using Python. Next, learn how to calculate singular-value decomposition and reconstruct a rectangular matrix; learn the characteristics of probability applicable in machine learning; and study probability in linear algebra and its role in machine learning. You will learn types of random variables and functions used to manage random numbers in probability; examine the concept and characteristics of central limit theorem and means and learn common usage scenarios; and examine the concept of parameter estimation and Gaussian distribution. Finally, learn the characteristics of binomial distribution with real-time examples.

14 videos |
1h 42m
Assessment
Badge
**Linear Regression Models: Introduction**

Machine learning (ML) is everywhere these days, often invisible to most of us. In this course, you will discover one of the fundamental problems in the world of ML: linear regression. Explore how this is solved with classic ML as well as neural networks. Key concepts covered here include how regression can be used to represent a relationship between two variables; applications of regression, and why it is used to make predictions; and how to evaluate the quality of a regression model by measuring its loss. Next, learn techniques used to make predictions with regression models; compare classic ML and deep learning techniques to perform a regression; and observe various components of a neural network and how they fit together. You will learn the two types of functions used in a neuron and their individual roles; how to calculate the optimal weights and biases of a neural network; and how to find the optimal parameters for a neural network.

13 videos |
1h 18m
Assessment
Badge
**Linear Regression Models: Building Models with Scikit Learn & Keras**

Learn how to use the Scikit Learn and Keras libraries to build a linear regression model to predict a house price. This course reviews the steps needed to prepare data and configure regression models. It shows how to prepare a data set to feed a linear regression model; how to use the Pandas library to load a CSV data set file; and how to configure, train, and validate linear regression models. The course also shows how to visualize metrics with Matplotlib; how to prepare data for a Keras model, how to learn the architecture for a Keras sequential model and initialize it; and finally, how train it to use optimal weights and biases for machine learning solutions.

9 videos |
41m
Assessment
Badge
**Linear Regression Models: Multiple & Parsimonious**

Several factors usually influence an outcome, and users need to consider all of those by using regression. Regression models help us mathematically evaluate our hunches. This course explores machine learning techniques and the risks involved with multiple factor linear regression. Key concepts covered here include reasons to use multiple features in a regression, and how to configure, train, and evaluate the linear regression model. Next, learn to create a data set with multiple features in a form that can be fed to a neural network for training and validation. Review Keras sequential model architecture, its training parameters, and ways to test its predictions. Learn how to use Pandas and Seaborn to view correlations and enumerate risks. Conclude by applying parsimonious regression to rebuild linear regression models.

12 videos |
1h 10m
Assessment
Badge
**Linear Regression Models: Introduction to Logistic Regression**

Logistic regression is a technique used to estimate the probability of an outcome for machine learning solutions. In this 10-video course, learners discover the concepts and explore how logistic regression is used to predict categorical outcomes. Key concepts covered here include the qualities of a logistic regression S-curve and the kind of data it can model; learning how a logistic regression can be used to perform classification tasks; and how to compare logistic regression with linear regression. Next, you will learn how neural networks can be used to perform a logistic regression; how to prepare a data set to build, train, and evaluate a logistic regression model in Scikit Learn; and how to use a logistic regression model to perform a classification task and evaluate the performance of the model. Learners observe how to prepare a data set to build, train, and evaluate a Keras sequential model, and how to build, train, and validate Keras models by defining various components, including activation functions, optimizers and the loss function.

11 videos |
57m
Assessment
Badge
**Simplifying Regression and Classification with Estimators**

This 6-video course focuses on understanding Google's TensorFlow estimators, and showing learners how they simplify the task of building simple linear and logistic regression models for machine learning solutions. As a prerequisite, learners should have a basic understanding of ML (machine learning), and basic experience programming in Python. Though not required, familiarity with the Scikit-learn library and the Keras API will simplify the labs part of this course. First, you will learn how TensorFlow estimators abstract many of the details in creating a neural network, and you will then learn that you no longer need to define the type of neural network model, nor will you need to add definitions to layer. When using an estimator, learners only need to feed in training and validation data. In the course labs, you will build both a linear regression model and a classifier by using TensorFlow estimators. Finally, you will learn how to evaluate your model using the prebuilt methods available in the estimator.

7 videos |
35m
Assessment
Badge
**Computational Theory: Language Principle & Finite Automata Theory**

In this 12-video course, learners will explore the concept of computational theory and its models by discovering how to model and implement computational theory on formal language, automata theory, and context-free grammar. Begin by examining the computational theory fundamentals and the prominent branches of computation, and also the prominent models of computation for machine learning. Then look at the concept of automata theory and list the prominent automata classes. Next, explore the finite state machine principles, and recognize the essential principles driving formal language theory and the automata theory principles. Learners will recall the formal language elements; define the concept of regular expressions; and list the theorems used to manage the semantics. Examine the concept of regular grammar and list the essential grammars used to generate regular languages. Also, examine regular language closure properties, and defining and listing the prominent features of context-free grammar. The concluding exercise involves identifying practical usage, branches, and models of computational theory, specifying notations of formal language, and listing types of context-free grammar.

12 videos |
44m
Assessment
Badge
**Computational Theory: Using Turing, Transducers, & Complexity Classes**

Discover the concepts of pushdown automata, Turing machines, and finite transducers in this 12-video course, in which learners can examine how to identify limitations and complexities in computation and how to apply P and NP classes to manage them. Begin by recalling the machine learning analytical capabilities of grammar, then look at context-free grammar normal forms, using Chomsky normal forms and Greibach normal forms to manage context-free grammars. Describe pushdown automata and features of nondeterministic pushdown automata. This leads on to Turing machines, their capabilities, and the prominent variations in the building themes of Turing machines. Learners explore the concept of finite transducers, and the types of finite transducers. Recall the underlying limitations of computations and the limitations of computational theory, and the complexities of computation, computational theory complexities, and how it can impact Turing machine models and language families. Learn about handling computation complexities with P class and handling computation complexities with NP class. The concluding exercise involves describing properties and variations of Turing machines, types of finite transducers, and properties of recursively enumerable languages.

12 videos |
46m
Assessment
Badge
**Model Management: Building Machine Learning Models & Pipelines**

In this course, you will explore various approaches to building and implementing machine learning (ML) models and pipelines and will learn how to manage classification and regression problems. Begin this 11-video course by taking a look at the differences between ML models and ML algorithms. You will go on to learn about the different types of ML models and will then explore the approaches to developing and building them. Discover how to create and save ML models by using scikit-learn, and learn to recognize the various models that can be used to manage classification and regression problems. Explore how to build ML pipelines and then examine the prominent tools that can be used. You will learn how to implement scikit-learn ML pipelines, and in the final tutorial, learners will recall the steps involved in iterative machine learning model management and the associated benefits. In the concluding exercise, you will be asked to build ML models and pipelines by using scikit-learn.

11 videos |
31m
Assessment
Badge
**Model Management: Building & Deploying Machine Learning Models in Production**

In this 14-video course, learners can explore hyperparameter tuning, versioning machine learning (ML) models, and preparing and deploying ML models in production. Begin the course by describing hyperparameter and the different types of hyperparameter tuning methods, and also learn about grid search hyperparameter tuning. Next, learn to recognize the essential aspects of a reproducible study; list ML metrics that can be used to evaluate ML algorithms; learn about the relevance of versioning ML models, and implement Git and DVC machine learning model versioning. Describe ModelDB architecture used for managing ML models, and list the essential features of the model management framework. Observe how to set up Studio.ml to manage ML models and create ML models in production, and examine Flask machine learning model setup for production. Explore how to deploy machine or deep learning models in production. The exercise involves tuning hyperparameter with grid search, versioning ML models by using Git, and creating ML models for production.

14 videos |
55m
Assessment
Badge
**Bayesian Methods: Bayesian Concepts & Core Components**

This 11-video course explores the machine learning concepts of Bayesian methods and the implementation of Bayes' theorem and methods in machine learning. Learners can examine Bayesian statistics and analysis with a focus on probability distribution and prior knowledge distribution. Begin with a look at the concept of Bayesian probability and statistical inference, then move on to the concept of Bayesian theorem and its implementation in machine learning. Next, learn about the role of probability and statistics in Bayesian analysis from the perspective of frequentist probability and subjective probability paradigms. You will examine standard probability, continuous distribution, and discrete distribution, and recall the essential elements of Bayesian statistics including prior distribution, likelihood function, and posterior inference. Recognize the implementation of prominent Bayesian methods including inference, statistical modeling, influence of prior belief, and statistical graphics. Describe prior knowledge and compare the differences between non-informative prior distribution and informative prior distribution. The steps involved in Bayesian analysis, including modeling data, deciding prior distribution, likelihood construction, and posterior distribution are also covered. The concluding exercise focuses on Bayesian statistics and analysis.

11 videos |
1h
Assessment
Badge
**Implementing Bayesian Model and Computation with PyMC**

Learners can examine the concept of Bayesian learning and the different types of Bayesian models in this 12-video course. Discover how to implement Bayesian models and computations by using different approaches and PyMC for your machine learning solutions. Learners start by exploring critical features of and difficulties associated with Bayesian learning methods, and then take a look at defining the Bayesian model and classifying single-parameter, multiparameter, and hierarchical Bayesian models. Examine the features of probabilistic programming and learn to list the popular probabilistic programming languages. You will look at defining Bayesian models with PyMC and arbitrary deterministic function and generating posterior samples with PyMC models. Next, learners recall the fundamental activities involved in the PyMC Bayesian data analysis process, including model checking, evaluation, comparison, and model expansion. Delve into the computation methods of Bayesian, including numerical integration, distributional approximation, and direct simulation. Also, look at computing with Markov chain simulation, and the prominent algorithms that can be used to find posterior modes based on the distribution approximation. The concluding exercise focuses on Bayesian modeling with PyMC.

12 videos |
47m
Assessment
Badge
**Bayesian Methods: Advanced Bayesian Computation Model**

This 11-video course explores advanced Bayesian computation models, as well as how to implement Bayesian modeling with linear regression, nonlinear, probabilistic, and mixture models. In addition, learners discover how to implement Bayesian inference models with PyMC3. First, learn how to build and implement Bayesian linear regression models by using Python for machine learning solutions. Examine prominent hierarchical linear models from the perspective of regression coefficients. Then view the concept of probability models and use of Bayesian methods for problems with missing data. You will discover how to build probability models by using Python, and examine coefficient shrinkage with nonlinear models, nonparametric models, and multivariate regression from nonlinear models. Examine fundamental concepts of Gaussian process models; the approaches of classification with mixture models and regression with mixture models; and essential properties of Dirichlet process models. Finally, learn how to implement Bayesian inference models in Python with PyMC3. The concluding exercise recalls hierarchical linear models from the perspective of regression coefficients, and asks learners to describe the approach of working with generalized linear models, and implement Bayesian inference by using PyMC3.

11 videos |
51m
Assessment
Badge
**Reinforcement Learning: Essentials**

Explore machine learning reinforcement learning, along with the essential components of reinforcement learning that will assist in the development of critical algorithms for decisionmaking, in this 10-video course. You will examine how to achieve continuous improvement in performance of machines or programs over time, along with key differences between reinforcement learning and machine learning paradigm. Learners will observe how to depict the flow of reinforcement learning by using agent, action, and environment. Next, you will examine different scenarios of state changes and transition processes applied in reinforcement learning. Then examine the reward hypothesis, and learn to recognize the role of rewards in reinforcement learning. You will learn that all goals can be described by maximization of the expected cumulative rewards. Continue by learning the essential steps applied by agents in reinforcement learning to make decisions. You will explore the types of reinforcement learning environments, including deterministic, observable, discrete or continuous, and single-agent or multi-agent. Finally, you will learn how to install OpenAI Gym and OpenAl Universe.

10 videos |
29m
Assessment
Badge
**Reinforcement Learning: Tools & Frameworks**

This 9-video course explores how to implement machine learning reinforcement learning by examining the terminology, including agents, the environment, state, and policy. This course demonstrates how to implement reinforcement learning by using Keras and Python; how to ensure that you can build a model; and how to launch and use Ubuntu, and VI editor to do score calculations. First, learn the role of the Markov decision process in which the agent observes the environment, with output consisting of a reward and the next state, and then acts upon it. You will explore Q-learning, a model-free reinforcement learning technique, an asynchronous dynamic programming approach, and will learn about the Q-learning rule, and Deep Q-learning. Next, learn the steps to install TensorFlow for reinforcement learning, as well as framework, which is used for reinforcement learning provided by OpenAI. Then learn how to implement TensorFlow for reinforcement learning. Finally, you will learn to implement Q-learning using Python, and then utilize capabilities of OpenAl Gym and FrozenLake.

9 videos |
34m
Assessment
Badge
**Math for Data Science & Machine Learning**

Explore the machine learning application of key mathematical topics related to linear algebra with the Python programming language in this 13-video course. The programming demonstrated in this course requires access to Python Jupyter, and requires a Python 3 Jupyter kernel. First, you will learn to work with vectors, ordered lists of numbers, in Python, and then examine how to use Python's NumPy library when working with linear algebra. Next, you will enlist the NumPy library and the array object to create a vector. Learners will continue by learning how to use the NumPy library to create a matrix, a multidimensional array, or a list of vectors. Then examine matrix multiplication and division, and linear transformations. You will learn how to use Gaussian elimination determinants and orthogonal matrices to solve a system of linear equations. This course examines the concepts of eigenvalues, eigenvectors, and eigendecomposition, a factorization of a matrix into a canonical form. Finally, you will learn how to work with pseudo inverse in Python.

14 videos |
1h 1m
Assessment
Badge
**Building ML Training Sets: Introduction**

There are numerous options available to scale and encode features and labels in data sets to get the best out of machine learning (ML) algorithms. In this 10-video course, explore techniques such as standardizing, nomalizing, and one-hot encoding. Learners begin by learning how to use Pandas library to load a data set in the form of a CSV file and perform exploratory analysis on its features. Then use scikit-learn's Binarizer to transform the continuous data in a series to binary values; apply the MiniMaxScaler on a data set to get two similar columns to have the same range of values; and standardize multiple columns in data sets with scikit-learn's StandardScaler. Examine differences between the Normalizer and other scaling techniques, and learn how to represent values in a column as a proportion of the maximum absolute value by using the MaxAbScaler. Finally, discover how to use Pandas library to one-hot encode one or more features of your data set and distinguish between this technique and label encoding. The concluding exercise involves building ML training sets.

10 videos |
1h 9m
Assessment
Badge
**Building ML Training Sets: Preprocessing Datasets for Linear Regression**

This 7-video course helps learners discover how to implement machine learning scaling techniques such as standardizing and min-max scaling on continuous data and one-hot encoding on categorical features to improve performance of linear regression models. In the first tutorial, you will use Pandas library to load a CSV file into a data frame and analyze its contents by using Pandas and Matplotlib. You will then learn how to create a linear regression model with scikit-learn to predict the sale price of a house and evaluate this model by using metrics such as mean squared error and r-square. Next, learners will examine the application of min-max scaling on continuous fields and one-hot encoding on the categorical columns of a data set. Then analyze effects of preprocessing by recognizing benefits of scaling and encoding data sets by evaluating the performance of a regression model built with preprocessed data. Also, learn how to use scikit-learn's StandardScaler on a data set's continuous features and compare its effects with that of min-max scaling. The concluding exercise involves preprocessing data for regression.

7 videos |
50m
Assessment
Badge
**Building ML Training Sets: Preprocessing Datasets for Classification**

In this course, learners can explore how to implement machine learning scaling techniques such as standardizing and normalizing on continuous data and label encoding on the target, in order to get the best out of machine learning algorithms. Examine dimensionality reduction by using Principal Component Analysis (PCA). Start this 6-video course by using Pandas library to load a CSV data set into a data frame and scale continuous features by using a standard scaler. You will then learn how to build and evaluate a support vector classifier in scikit-learn; use Pandas and Seaborn to generate a heat map; and spot the correlations between features in a data set. Discover how to apply the technique of PCA to reduce the number of dimensions in your input data and obtain the explained variance of each principal component. In the course's final tutorial, you will explore how to apply normalization and PCA on data sets and build a classification model with the principal components of scaled data. The concluding exercise involves processing data for classification.

6 videos |
43m
Assessment
Badge
**Linear Models & Gradient Descent: Managing Linear Models**

Explore the concept of machine learning linear models, classifications of linear models, and prominent statistical approaches used to implement linear models. This 11-video course also explores the concepts of bias, variance, and regularization. Key concepts covered here include learning about linear models and various classifications used in predictive analytics; learning different statistical approaches that are used to implement linear models [single regression, multiple regression and analysis of variance (ANOVA)]; and various essential components of a generalized linear model (random component, linear predictor and link function). Next, discover differences between the ANOVA and analysis of covariance (ANCOVA) approaches of statistical testing; learn about implementation of linear regression models by using Scikit-learn; and learn about the concepts of bias, variance, and regularization and their usages in evaluating predictive models. Learners explore the concept of ensemble techniques and illustrate how bagging and boosting algorithms are used to manage predictions, and learn to implement bagging algorithms with the approach of random forest by using Scikit-learn. Finally, observe how to implement boosting ensemble algorithms by using Adaboost classifier in Python.

11 videos |
47m
Assessment
Badge
**Linear Models & Gradient Descent: Gradient Descent and Regularization**

Explore the features of simple and multiple regression, implement simple and multiple regression models, and explore concepts of gradient descent and regularization and different types of gradient descent and regularization. Key concepts covered in this 12-video course include characteristics of the prominent types of linear regression; essential features of simple and multiple regressions and how they are used to implement linear models; and how to implement simple regression models by using Python libraries for machine learning solutions. Next, observe how to implement multiple regression models in Python by using Scikit-learn and StatsModels; learn the different types of gradient descent; and see how to classify the prominent gradient descent optimization algorithms from the perspective of their mathematical representation. Learn how to implement a simple representation of gradient descent using Python; how to implement linear regression by using mini-batch gradient descent to compute hypothesis and predictions; and learn the benefits of regularization and the objectives of L1 and L2 regularization. Finally, learn how to implement L1 and L2 regularization of linear models by using Scikit-learn.

12 videos |
53m
Assessment
Badge
**Final Exam: ML Programmer**

Final Exam: ML Programmer will test your knowledge and application of the topics presented throughout the ML Programmer track of the Skillsoft Aspire ML Programmer to ML Architect Journey.

1 video |
32s
Assessment
Badge
**COURSES INCLUDED**

**Getting Started with Neural Networks: Biological & Artificial Neural Networks**

Learners can explore fundamental concepts of biological and artificial neural networks, computational models that can be implemented with neural networks, and how to implement neural networks with Python, in this 12-video course. Begin with a look at characteristics of machine learning biological neural networks that inspired artificial neural networks. Then explore components of biological neural networks and the signal processing mechanism. Next, take a look at the essential components of the structure of artificial neural networks; learn to recognize the layered architecture of neural networks; and observe how to classify various computational models that can be implemented by using neural networks paradigm. Examine neurons connectivity, by describing the interconnection between neurons involving weights and fixed weights. This leads on to threshold functions in neural networks and the basic logic gates of AND, OR, and XNOR. Implement neural networks by using Python and the core libraries provided by Python for neural networks; create a neural network model using Python, Keras, and TensorFlow, and finally, view prominent neural network use cases. The concluding exercise involves implementing neural networks.

12 videos |
58m
Assessment
Badge
**Getting Started with Neural Networks: Perceptrons & Neural Network Algorithms**

Discover the basics of perceptrons, including single- layer and multilayer, and the roles of linear and nonlinear functions in this 10-video course. Learners will explore how to implement perceptrons and perceptron classifiers by using Python for machine learning solutions. Key concepts covered in this course include perceptrons, single-layer and multilayer perceptrons, and the computational role they play in artificial neural networks; learning the algorithms that can be used to implement single-layer perceptron training models; and exploring multilayer perceptrons and illustrating the algorithmic difference from single-layer perceptrons. Next, you will learn to classify the role of linear and nonlinear functions in perceptrons; learn how to implement perceptrons by using Python; and learn approaches and benefits of using the backpropagation algorithm in neural networks. Then learn the uses of linear and nonlinear activation functions in artificial neural networks; learn to implement a simple perceptron classifier using Python; and learn the benefits of using the backpropagation algorithm in neural networks and implement perceptrons and perceptron classifiers by using Python.

10 videos |
44m
Assessment
Badge
**Building Neural Networks: Development Principles**

Explore essential machine learning components used to learn, train, and build neural networks and prominent clustering and classification algorithms in this 12-video course. The use of hyperparameters and perceptrons in artificial neuron networks (ANNs) is also covered. Learners begin by studying essential ANN components required to process data, and also different paradigms of learning used in ANN. Examine essential clustering techniques that can be applied on ANN, and the roles of the essential components that are used in building neural networks. Next, recall the approach of generating deep neural networks from perceptrons; learn how to classify differences between models and hyperparameters and specify the approach of tuning hyperparameters. You will discover types of classification algorithm that can be used in neural networks, and features of essential deep learning frameworks for building neural networks. Explore how to choose the right neural network framework for neural network implementations from the perspective of usage scenarios and fitment model, and define computational models that can be used to build neural network models. The concluding exercise concerns ANN training and classification.

12 videos |
1h 20m
Assessment
Badge
**Building Neural Networks: Artificial Neural Networks Using Frameworks**

This 13-video course helps learners discover how to implement various neural networks scenarios by using Python, Keras, and TensorFlow for machine learning. Learn how to optimize, tune, and speed up the processes of artificial neural networks (ANN) and how to implement predictions with ANN is also covered. You will begin with a look at prominent building blocks involved in building a neural network, then recalling the concept and characteristics of evolutionary algorithms, gradient descent, and genetic algorithms. Learn how to build neural networks with Python and Keras for classification with Tensorflow as the backend. Discover how to build neural networks by using PyTorch; implement object image classification using neural network algorithms; and define and illustrate the use of learning rates to optimize deep learning. Examine various parameters and approaches of optimizing neural network speed; learn how to select hyperparameters and tune for dense networks by using Hyperas; and build linear models with estimators by using the capabilities of TensorFlow. Explore predicting with neural networks, temporal prediction optimization, and heterogenous prediction optimization. The concluding exercise involves building neural networks.

13 videos |
1h 54m
Assessment
Badge
**Training Neural Networks: Implementing the Learning Process**

In this 13-video course, learners can explore how to work with machine learning frameworks and Python to implement training algorithms for neural networks. You will learn the concept and characteristics of perceptrons, a single layer neural network that aggregates the weighted sum of inputs, and returns either zero or one, and neural networks. You will then explore some of the prominent learning rules that to apply in neural networks, and the concept of supervised and unsupervised learning. Learn several types of neural network algorithms, and several training methods. Next, you will learn how to prepare and curate data by using Amazon SageMaker, and how to implement an artificial neural network training process using Python, and other prominent and essential learning algorithms to train neural networks. You will learn to use Python to train artificial neural networks, and how to use Backpropagation in Keras to implement multilayer perceptrons or neural networks. Finally, this course demonstrates how to implement regularization in multilayer perceptrons by using Keras.

13 videos |
1h 38m
Assessment
Badge
**Training Neural Networks: Advanced Learning Algorithms**

This 15-video course explores how to design advanced machine learning algorithms by using training patterns, pattern association, the Hebbian learning rule, and competitive learning. First, learners examine the concepts and characteristics of online and offline training techniques in implementing artificial neural networks, and different training patterns in teaching inputs that are used in implementing artificial neural networks. You will learn to manage training samples, and how to use Google Colab to implement overfitting and underfitting scenarios by using baseline models. You will examine regularization techniques to use in training artificial neural networks. This course then demonstrates how to train previously-built neural network models using Python, and the prominent training algorithms to implement pattern associations. Next, learn the architecture and algorithm associated with learning vector quantization; the essential phases involved in implementing Hebbian learning; how to implement Hebbian learning rule using Python; and the steps involved in implementing competitive learning. Finally, you will examine prominent techniques to use to optimize neural networks, and how to debug neural networks.

15 videos |
1h 40m
Assessment
Badge
**Improving Neural Networks: Neural Network Performance Management**

In this 12-video course, learners can explore machine learning problems that can be addressed with hyperparameters, and prominent hyperparameter tuning methods, along with problems associated with hyperparameter optimization. Key concepts covered here include the iterative workflow for machine learning problems, with a focus on essential measures and evaluation protocols; steps to improve performance of neural networks, along with impacts of data set sizes on neural network models and performance estimates; and impact of the size of training data sets on quality of mapping function and estimated performance of a fit neural network model. Next, you will learn the approaches of identifying overfitting scenarios and preventing overfitting by using regularization techniques; learn the impact of bias and variances on machine learning algorithms, and recall the approaches of fixing high bias and high variance in data sets; and see how to trade off bias variance by building and deriving an ideal learning curve by using Python. Finally, learners will observe how to test multiple models and select the right model by using Scikit-learn.

12 videos |
1h 56m
Assessment
Badge
**Improving Neural Networks: Loss Function & Optimization**

Learners can explore the concept of loss function, the different types of Loss function and their impact on neural networks, and the causes of optimization problems, in this 10-video course. Examine alternatives to optimization, the prominent optimizer algorithms and their associated properties, and the concept of learning rates in neural networks for machine learning solutions. Key concepts in this course include learning loss function and listing various types of loss function; recognizing impacts of the different types of loss function on neural networks models; and learning how to calculate loss function and score by using Python. Next, learners will learn to recognize critical causes of optimization problems and essential alternatives to optimization; recall prominent optimizer algorithms, along with their properties that can be applied for optimization; and how to perform comparative optimizer analysis using Keras. Finally, discover the relevance of learning rates in optimization and various approaches of improving learning rates; and learn the approach of finding learning rate by using RMSProp optimizer.

10 videos |
1h 3m
Assessment
Badge
**Improving Neural Networks: Data Scaling & Regularization**

Explore how to create and optimize machine learning neural network models, scaling data, batch normalization, and internal covariate shift. Learners will discover the learning rate adaptation schedule, batch normalization, and using L1 and L2 regularization to manage overfitting problems. Key concepts covered in this 10-video course include the approach of creating deep learning network models, along with steps involved in optimizing networks, including deciding size and budget; how to implement the learning rate adaptation schedule in Keras by using SGD and specifying learning rate, epoch, and decay using Google Colab; and scaling data and the prominent data scaling methods, including data normalization and data standardization. Next, you will learn the concept of batch normalization and internal covariate shift; how to implement batch normalization using Python and TensorFlow; and the steps to implement L1 and L2 regularization to manage overfitting problems. Finally, observe how to implement gradient descent by using Python and the steps related to library import and data creation.

10 videos |
1h 37m
Assessment
Badge
**ConvNets: Introduction to Convolutional Neural Networks**

Explore convolutional neural networks, their different types, and prominent use cases for machine learning, in this 10-video course. Learners will study the different layers and parameters of convolutional neural networks and their roles in implementing and addressing image recognition and classification problems. Key concepts covered in this course include the working mechanisms of convolutional neural networks, and the different types of convolutional neural networks that we can implement; and problems associated with computer vision, along with the prominent techniques to manage them. Next, you will learn about the role of neural networks and convolutional neural networks in implementing and addressing image recognition and classification problems; observe the prominent layers and parameters of convolutional neural networks for image classification; and learn to see the convolutional layer from a mathematical perspective, while recognizing the mathematical elements that enter into the convolution operations. Finally, learners will be shown how to build a convolutional neural network for image classification by using Python.

10 videos |
1h
Assessment
Badge
**ConvNets: Working with Convolutional Neural Networks**

Learners can explore the prominent machine learning elements that are used for computation in artificial neural networks, the concept of edge detection, and common algorithms, as well as convolution and pooling operations, and essential rules of filters and channel detection, in this 10-video course. Key concepts covered here include the architecture of neural networks, along with essential elements used for computations by focusing on Softmax classifier; how to work with ConvNetJS as a Javascript library and train deep learning models; and learning about the edge detection method, including common algorithms that are used for edge detection. Next, you will examine the series of convolution and pooling operations used to detect features; learn the involvement of math in convolutional neural networks and essential rules that are applied on filters and channel detection; and learn principles of convolutional layer, activation function, pooling layer, and fully-connected layer. Learners will observe the need for activation layers in convolutional neural networks and compare prominent activation functions for deep neural networks; and learn different approaches to improve convolution neural networks and machine learning systems.

10 videos |
42m
Assessment
Badge
**Convolutional Neural Networks: Fundamentals**

Learners can explore the concepts of convolutional neural network (CNN); the underlying architecture, principles, and methods needed to build a CNN; and its implementation in a deep neural network. In this 12-video course, you will examine visual perception, and the ability to interpret the surrounding environment by using light in the visible spectrum. First, learn about CNN architecture; how to analyze the essential layers; and the impact of an initial choice of layers. Next, you will learn about nonlinearity in the first layer, and the need for several pooling techniques. Then learn how to implement a convolutional layer and sparse interaction. Examine the hidden layers of CNN, which are convolutional layers, ReLU (rectified linear unit) layers, or activation functions, the pooling layers, the fully connected layer, and the normalization layer. You will examine machine learning semantic segmentation to understand an image at the pixel level, and its implementation using Texton Forest and a random based classifier. Finally, this course examines Gradient Descent and its variants.

12 videos |
45m
Assessment
Badge
**Convolutional Neural Networks: Implementing & Training**

This course explores machine learning convolutional neural networks (CNNs), which are popular for implementation in image and audio processing. Learners explore AI (artificial intelligence), and the issues surrounding implementation, how to approach organizational talent and strategy, and how to prepare for AI architecture in this 8-video course. You will learn to use the Google Colab tool, and to implement image recognition classifier by using CNN, Keras, and TensorFlow. Next, learn to install and implement a model, and use it for image classification. You will examine the artificial neural network ResNet (residual neural network), and how it builds on constructs known from pyramidal cells and cerebral cortex. You will also study PyTorch, an open-source machine learning library that enables fast, flexible experimentation, and efficient production through a hybrid front end, and learn to use the PyTorch ecosystem tool to develop and implement neural networks. Finally, this course demonstrates how to create a data set by using Training CNN by using PyTorch to categorize garments.

8 videos |
30m
Assessment
Badge
**Convo Nets for Visual Recognition: Filters and Feature Mapping in CNN**

In this 13-video course, you will explore the capabilities and features of convolutional networks for machine learning that make it a recommended choice for visual recognition implementation. Begin by examining the architecture and the various layers of convolutional networks, including pooling layer, convo layer, normalization layer, and fully connected layer, and defining the concept and types of filters in convolutional networks along with their usage scenarios. Learn about the approach to maximizing filter activation with Keras; define the concept of feature map in convolutional networks and illustrate the approach of visualizing feature maps; and plot the map of the first convo layer for given images, then visualize the feature map output from every block in the visual geometry group (VGG) model. Look at optimization parameters for convolutional networks, and hyperparameters for tuning and optimizing convolutional networks. Learn about applying functions on pooling layer; pooling layer operations; implementing pooling layer with Python, and implementing convo layer with Python. The concluding exercise involves plotting feature maps.

13 videos |
1h 6m
Assessment
Badge
**Convo Nets for Visual Recognition: Computer Vision & CNN Architectures**

Learners can explore the machine learning concept and classification of activation functions, the limitations of Tanh and the limitations of Sigmoid, and how these limitations can be resolved using the rectified linear unit, or ReLU, along with the significant benefits afforded by ReLU, in this 10-video course. You will observe how to implement ReLU activation function in convolutional networks using Python. Next, discover the core tasks used in implementing computer vision, and developing CNN models from scratch for object image classification by using Python and Keras. Examine the concept of the fully-connected layer and its role in convolutional networks, and also the CNN training process workflow and essential elements that you need to specify during the CNN training process. The final tutorial in this course involves listing and comparing the various convolutional neural network architectures. In the concluding exercise you will recall the benefits of applying ReLU in CNNs, list the prominent CNN architectures, and implement ReLU function in convolutional networks using Python.

10 videos |
48m
Assessment
Badge
**Fundamentals of Sequence Model: Artificial Neural Network & Sequence Modeling**

Explore artificial neural networks (ANNs), their essential components, tools, and frameworks for their implementation in machine learning solutions. In this 9-video course, you will discover recurrent neural networks (RNNs) and how they are implemented. Key concepts covered here include perceptrons and the computational role they play in ANNs; learning features and characteristics of ANNs and how components are used to build a model; and learning prominent tools and frameworks used to implement sequence models and ANNs. Next, you will learn about sequence modeling as it pertains to language models; RNNs and their capabilities and components; and how to specify RNN types and their implementation features. Learners will then explore the concept of linear and nonlinear functions and classify how they are used with perceptrons; explore the concept of backpropagation and usage of backpropagation algorithm in neural networks; and examine the concept of activation functions and how linear and nonlinear activations are utilized in neural networks. Finally, you will see how to implement perceptrons with Python, and how to use modeling tools and architectures and applications of sequence models.

9 videos |
36m
Assessment
Badge
**Fundamentals of Sequence Model: Language Model & Modeling Algorithms**

In this 7-video course, learners can explore the concepts of language modeling, natural language processing (NLP), and sequence generation for NLP. Prominent machine learning modeling algorithms such as vanishing gradient problem, gated recurrent units (GRUs), and long short-term memory (LSTM) network are also covered. Key concepts studied in this course include language models, one of the most important parts of NLP. and how to implement NLP along with its essential components; learning the process and approach of generating sequence for NLP; and vanishing gradient problem implementation approaches to overcome the problem of taking longer times to achieve convergence. Then, learn about features and characteristics of GRUs used to resolve issues with vanishing gradient problems, and learn the problems and drawbacks of implementing short-term memory and LSTM as modeling solutions. In the concluding exercise, learners will review the essential components and prominent applications of language modeling and specify some of the solutions for vanishing gradient problems.

7 videos |
18m
Assessment
Badge
**Build & Train RNNs: Neural Network Components**

Explore the concept of artificial neural networks (ANNs) and components of neural networks, and examine the concept of learning and training samples used in supervised, unsupervised, and reinforcement learning in this 10-video course. Other topics covered in this course include network topologies, neuron activation mechanism, training sets, pattern recognition, and the need for gradient optimization procedure for machine learning. You will begin the course with an overview of ANN and its components, then examine the artificial network topologies that implement feedforward, recurrent, and linked networks. Take a look at the activation mechanism for neural networks, and the prominent learning samples that can be applied in neural networks. Next, compare supervised learning samples, unsupervised learning samples, and reinforcement learning samples, and then view training samples and the approaches to building them. Explore training sets and pattern recognition and, in the final tutorial, examine the need for gradient optimization in neural networks. The exercise involves listing neural network components, activation functions, learning samples, and gradient descent optimization algorithms.

10 videos |
36m
Assessment
Badge
**Build & Train RNNs: Implementing Recurrent Neural Networks**

Learners will examine the concepts of perception, layers of perception, and backpropagation, and discover how to implement recurrent neural network by using Python, TensorFlow, and Caffe2 in this 10-video course. Begin by taking a look at the essential features and processes of implementing perception and backpropagation in machine learning neural networks. Next, you will compare single-layer perception and multilayer perception and describe the need for layer management. You will learn about the steps involved in building recurrent neural network models; building recurrent neural networks with Python and TensorFlow; implementing long short-term memory (LSTM) by using TensorFlow, and building recurrent neural networks with Caffe2. Caffe is a deep learning framework. Building deep learning language models using Keras-an open source neural network library-will be explored in the final tutorial of the course. The concluding exercise entails implementing recurrent neural networks by using TensorFlow and Caffe2 and building deep learning language models by using Keras.

10 videos |
48m
Assessment
Badge
**ML Algorithms: Multivariate Calculation & Algorithms**

Learners can explore the role of multivariate calculus in machine learning (ML), and how to apply math to data science, ML, and deep learning, in this 10-video course examining several ML algorithms, and showing how to identify different types of variables. First, learners will observe how to implement multivariate calculus, derive function representations of calculus, and utilize differentiation and linear algebra to optimize ML algorithms. Next, you will examine how to use advanced calculus and discrete optimization, to implement robust, and high-performance ML applications. Then you will learn to use R and Python to implement multivariate calculus for ML and data science. You will learn about partial differentiation, and its application on vector calculus and differential geometry, and the use of product rule and chain rule. You will examine the role of linear algebra in ML, and learn to classify the techniques of optimization by using gradient and Jacobian matrix. Finally, you will explore Taylor's theorem and the conditions for local minimum.

10 videos |
38m
Assessment
Badge
**ML Algorithms: Machine Learning Implementation Using Calculus & Probability**

This course explores the use of multivariate calculus, derivative function representations, differentiation, and linear algebra to optimize ML (machine learning) algorithms. In 10 videos, learners will observe how to use probability theory to enable prediction and other analytical types in ML, including the role of probability in chain rule and Bayes' rule. First, you will explore the concepts of variance, covariance, and random vectors, before examining Likelihood and Posteriori estimation. Next, learn how to use estimation parameters to determine the best value of model parameters through data assimilation, and how it can be applied to ML. You will explore the role of calculus in deep learning, and the importance of derivatives in deep learning. Continue by learning optimization functions such as gradient descent, and whether to increase or decrease weight to maximize or minimize some metrics. You will learn to implement differentiation and integration in R and how to implement calculus derivatives, integrals using Python. Finally, you will examine the use of limits and series expansion in Python.

10 videos |
30m
Assessment
Badge
**Final Exam: DL Programmer**

Final Exam: DL Programmer will test your knowledge and application of the topics presented throughout the DL Programmer track of the Skillsoft Aspire ML Programmer to ML Architect Journey.

1 video |
32s
Assessment
Badge
**COURSES INCLUDED**

**Predictive Modeling: Predictive Analytics & Exploratory Data Analysis**

Explore the machine learning predictive analytics, exploratory data analytics, and different types of data sets and variables in this 9-video course. Discover how to implement predictive models and manage missing values and outliers by using Python frameworks. Key concepts covered in this course include predictive analytics, a branch of advanced analytics, and its process flow, and learning how analytical base tables can be used to build and score analytical models. Next, you will discover business problems that can be resolved by using predictive modeling; how to build predictive models with the Python framework; and learn the essential features of exploratory data analysis. Then learn about data sets, collections of data corresponding to the content of a single database or a single statistical data matrix, and then learn the variables of the different types of data sets including univariate, bivariate, and multivariate data and analytical approaches that can be implemented with them. Finally, you will learn about methods that can be used to manage missing values and outliers in data sets.

9 videos |
40m
Assessment
Badge
**Predictive Modeling: Implementing Predictive Models Using Visualizations**

Explore how to work with machine learning feature selection, general classes of feature selection algorithms, and predictive modeling best practices. In this 12-video course, learners discover how to implement predictive models with scatter plots, boxplots, and crosstabs by using Python. Key concepts examined here include the benefits of feature selection and the general classes of feature selection algorithms; the different types of predictive models that can be implemented and associated features; and how to implement scatterplots and the capability of scatterplots in facilitating predictions. Next, you will learn about Pearson's correlation measures and the possible ranges for Pearson's correlation; learn to recognize the anatomy of a boxplot, a visual representation of the statistical five-number summary of a given data set; and observe how to create and interpret boxplots with Python. Then see how to implement crosstabs to visualize categorical variables; learn statistical concepts that are used for predictive modeling; and learn tree-based methods used to implement regression and classification. Finally, you will learn best practices for implementing predictive modeling.

12 videos |
41m
Assessment
Badge
**Applying Predictive Analytics**

This 13-video course explores machine learning predictive analytics, and how its application can drive revenues, reduce costs, and provide a competitive advantage to businesses. Learners will observe the predictive modeling process and how to apply tools and techniques for performing predictive analytics, and how to use historical data to identify trends and patterns to forecast future events. First, you will learn about the predicative modeling process, the statistical concepts for predictive modeling, and regression techniques. This course uses two examples to demonstrate commonly used methods of predictive analytics, by examining decision trees and SVMs (support vector machines). Next, you will learn about survival analysis, market basket analysis, and how to apply data for cluster models. You will learn about random forests in predictive analytics, and you will examine probabilistic graphical models. Learn about classification models, and how to organize data into groups based on predicting the class of the data points. Finally, you will explore some best practices for predictive modeling.

14 videos |
1h 25m
Assessment
Badge
**Planning AI Implementation**

This 13-video course explores how artificial intelligence (AI) can be leveraged, how to plan an AI implementation from setup to architecture, and the issues surrounding incorporating it into an enterprise for machine learning. Learners will explore the three legs of AI: how it applies intelligence-like behavior to machines. You will then examine how machine learning adds to this intelligence-like behavior, and the next generation with deep learning. This course discusses strategies for implementation of AI, organizational challenges surrounding the adoption of AI, and the need for training of both personnel and machines. Next, learn the role of data and algorithms in AI implementation. Learners continue by examining several ways in which an organization can plan and develop AI capability; the elements organizations need to understand how to assess AI needs and tools; management challenges; and the impact on personnel. You will learn about pitfalls in using AI, and what to avoid. Finally, you will learn about data issues, data quality, training concepts, overfitting, and bias.

13 videos |
44m
Assessment
Badge
**Automation Design & Robotics**

In this 12-video course, you will examine the different uses of data science tools and the overall platform, as well as the benefits and challenges of machine learning deployment. The first tutorial explores what automation is and how it is implemented. This is followed by a look at the tasks and processes best suited for automation. This leads learners into exploring automation design, including what Display Status is, and also the Human-Computer Collaboration automation design principle. Next, you will examine the Human Intervention automation design principle; automated testing in software design and development; and also the role of task runners in software design and development. Task runners are used to automate repeatable tasks in the build process. Delve into DevOps and automated deployment in software design, development, and deployment. Finally, you will examine process automation using robotics, and in the last tutorial in the course, recognize how modern robotics and AI designs are applied. The concluding exercise involves recognizing automation and robotics design application.

13 videos |
34m
Assessment
Badge
**ML/DL in the Enterprise: Machine Learning Modeling, Development, & Deployment**

This 13-video course explores various standards and frameworks that can be adopted to build, deploy, and implement machine learning (ML) models and workflows. Begin with a look at the critical challenges that may be encountered when implementing ML. Examine essential stages of ML processes that need to be adopted by enterprises. Then explore the development lifecycle exclusively used to build productive ML models, and the essential phases of ML workflows. Recall the critical processes involved in training ML models; observe the various on-premises and cloud-based platforms for ML; and view the approaches that can be adopted to model and process data for productive ML deployments. Next, see how to set up a ML environment by using H2O clusters; recall various data stores and data management frameworks used as a data layer for ML environments; and specify the processes involved in implementing ML pipelines and using visualizations to generate insights. Finally, set up and work with Git to facilitate team-driven development and coordination across the enterprise. The concluding exercise concerns ML training processes.

13 videos |
1h 4m
Assessment
Badge
**ML/DL in the Enterprise: Pipelines & Infrastructure**

Learners will discover the infrastructure, frameworks, and tools that can be used to build data pipelines and visualization for machine learning (ML) in this 10-video course exploring end-to-end approaches for building and deploying ML applications. You will begin with a look at approaches to identifying the right infrastructure for data and ML, and building data pipelines for ML deployments. Examine the iterative process in building ML models with Machine Learning Studio; implement machine learning visualization, and classify frameworks and tools for ML. Next, observe how to build generalized low-rank models by using H2O and integrate them into a data science pipeline to make better predictions. Explore the role of model metadata in applying governance in ML, and also ML risk mitigation-recognizing how ML risk analysis and management approaches can be used to mitigate risks effectively. In the exercise you will recall learning build and deployment frameworks, use Python to implement visualization for ML, and build a simple ML model by using Microsoft Azure Machine Learning Studio.

10 videos |
53m
Assessment
Badge
**Enterprise Services: Enterprise Machine Learning with AWS**

This course explores features and operational benefits of using a cloud platform to implement machine learning (ML). In this 15-video course, learners observe how to manage diversified kinds of data, and the exponential growth of unstructured and structured data. First, you will examine ML workflow and compare differences between ML model development and traditional enterprise software development. Then you will learn how to use the ML services provided by AWS (Amazon Web Services) to implement end-to-end ML solutions at scale. Next, learners will examine AWS ML tools, services, and capabilities, the architecture, and internal components in Amazon SageMaker. You will continue by learning how to use Amazon Machine Learning Console to create data sources, implement ML models, and to use the models to facilitate predictions. This course compares the ML implementation scenarios and solutions in AWS, Microsoft Azure, and Google Cloud, and helps learners identify the best fit for any given scenario. Finally, you learn to use SageMaker and SageMaker Neo to create, train, tune, and deploy ML models anywhere.

15 videos |
1h 13m
Assessment
Badge
**Enterprise Services: Machine Learning Implementation on Microsoft Azure**

Explore the features and operational benefits of using a cloud platform to implement ML (machine learning) by using Microsoft Azure and Amazon SageMaker, in this 14-video course. First, you will learn how to use Microsoft Azure ML tools, services, and capabilities, and how to examine MLOps (machine learning and operations) to manage, deploy, and monitor models for quality and consistency. You will create Azure Machine Learning workspaces, and learn to configure development environments, build, and manage ML pipelines, to work with data sets, train models, and projects. You will develop and deploy predictive analytic solutions using the Azure Machine Learning Service visual interface, and work with Azure Machine Learning R Notebooks to fit and publish models. You will learn to enable CI/CD (continuous integration and continuous delivery) with Azure Pipelines, and examine ML tools in AWS (Amazon Web Services) SageMaker, and how to use Amazon's ML console. Finally, you will learn to track code from Azure Repos or GitHub, trigger release pipelines, and automate ML deployments by using Azure Pipelines.

14 videos |
1h 12m
Assessment
Badge
**Enterprise Services: Machine Learning Implementation on Google Cloud Platform**

This course explores the GCP (Google Cloud Platform) machine learning (ML) tools, services, and capabilities, and different stages in the Google Cloud Platform machine learning workflow. This 14-video course demonstrates a high-level overview of different stages in Google Cloud Platform machine learning workflow. You will examine the features of BigQuery, and how to use Big Query ML to create and evaluate a binary logistic regression model using Big Query ML statement. Next, learners will observe how to use the Google AI Platform and Google Cloud AutoML components and features used for training, evaluating, and deploying ML models. You will learn to train models by using the built-in linear learner algorithm, submit jobs with GCloud and Console, create and evaluate binary logistic regression models, and set up and work with Cloud Datalab. You will learn to use AutoML Tables to work with data sets, to train machine learning models for predictions. Finally, you will work with Google Cloud AutoML Natural Language to create custom ML models for content category classification.

14 videos |
1h
Assessment
Badge
**Enterprise Architecture: Architectural Principles & Patterns**

In this 18-video course, learners can explore software architecture concepts, including the view model, consumer-driven contracts, architectural patterns, and architectural styles and solution patterns used to manage common machine learning issues. Begin by examining software architecture and the benefits it provides, and then the principles that should be followed when designing architecture for applications. You will discover the 4+1 view model and associated views, and learn to recognize software architectures, and the principles of developing enterprise architecture. Recall architectural principles for business, data, and technology, and the fundamental principles guiding service-oriented architecture (SOA) and use of the SOA maturity model. Next, explore serverless architecture; Backend-as-a-Service; the features of evolutionary architecture; and learn to recognize benefits of documenting architecture. Examine the structure of a software project team; the concept and characteristics of consumer-driven contracts; the dimensions of architecture that should be coupled to provide maximize benefit with minimal overheads and costs; and activities and tasks that software architects perform. Finally, take a look at architectural patterns and styles that can be adopted to eliminate common problems.

18 videos |
1h 34m
Assessment
Badge
**Enterprise Architecture: Design Architecture for Machine Learning Applications**

Explore software architectures used to model machine learning (ML) applications in production, as well as the building blocks of ML reference architecture, in this 11-video course. Examine the pitfalls and building approaches for evolutionary architectures, Fitness function categories, architectural planning guidelines for ML projects, and how to set up complete ML solutions. Learners will begin by studying the basic architecture required to execute ML in enterprises, and will also take a look at software architecture and its features that can be used to model ML apps in production. Next, learn how to set up model ML apps; examine ML reference architecture and the associated building blocks; and view the approaches for building evolvable architectures and migration. Recognize the critical pitfalls of evolutionary architecture and antipatterns of technical architecture and change. Finally, observe how to set up complete ML solutions and explore the Fitness function and its associated categories. Conclude the course with an exercise on architectural planning guidelines for ML projects, with a focus on model refinement, testing, and evaluating production readiness.

11 videos |
59m
Assessment
Badge
**Architecting Balance: Designing Hybrid Cloud Solutions**

In this 12-video course, learners can explore differences between on-premises and hybrid cloud deployment and the challenges and benefits afforded by hybrid cloud architecture for machine learning solutions. Discover how to derive goals and design process for a successful hybrid cloud implementation. Begin by examining essential features afforded by cloud and cloud deployment models, and compare characteristics of on-premises and cloud deployment from perspectives of cost, hardware, software, mobility, and reliability. View factors influencing on-premises and cloud architecture; compare hybrid versus private versus public cloud; and use hybrid cloud assessment to identify appropriate scenarios for adopting a hybrid cloud architecture. Learners will be able to list essential factors to consider when deriving a hybrid cloud implementation strategy and architecture, and benefits and challenges of implementing hybrid cloud. Look at key considerations to determine whether to move and deploy applications to the cloud or retain them on on-premises environment, and demonstrate the steps involved in setting up hybrid cloud architecture. The concluding exercise involves recalling benefits of hybrid cloud and the differences between on-premises and hybrid cloud deployment models.

12 videos |
56m
Assessment
Badge
**Architecting Balance: Hybrid Cloud Implementation with AWS & Azure**

Explore the various services and components provided by Amazon Web Services (AWS) and Azure that can be used to implement hybrid cloud machine learning solution in this 13-video course. You will discover how to implement hybrid cloud environments by using AWS and Azure Stack. Learners begin by examining the critical use cases of implementing hybrid cloud using AWS, and the prominent AWS services that can be used to implement hybrid cloud solutions. Explore the cloudbursting application hosting model from the perspective of AWS, and recall the essential AWS services that provide integrated resource deployment management capabilities for hybrid cloud solutions. Implement a hybrid cloud environment that integrates on-premises Hadoop clusters with data lakes on AWS; recall the recommended principles and best practices of AWS hybrid cloud implementation, and essential Azure components for hybrid solutions. Explore Azure tooling for hybrid cloud; hybrid cloud implementation with Azure Stack; Azure DevOps for hybrid cloud; implementing hybrid cloud with Azure; and Azure services for hybrid cloud. The concluding exercise involves implementing a hybrid cloud with Azure.

13 videos |
1h 7m
Assessment
Badge
**Refactoring ML/DL Algorithms: Techniques & Principles**

Explore techniques of refactoring code, the process of changing a computer program source code without modifying its external functional behavior, in this 14-video course exploring design patterns and challenges in refactoring code. First, learn the essential machine learning principles when planning code, including how to identify what instead of how, and to look for consistencies. You will then learn to recognize the causes of technical debts that contribute to challenges in existing code. Next, you will learn code refactoring techniques and types of processes that you can use to eliminate deficiencies in the code. This course demonstrates the refactoring capabilities provided by PyCharm to refactor Python code, and the steps involved in optimizing Python code. You will learn static code analysis of Python by using Prospector, refactoring code to ensure backward compatibility, and the role of design patterns in code refactoring, and how to use rope to refactor Python code. Finally, you will learn to recall the prominent antipatterns that potentially complicate code and code refactoring.

14 videos |
1h 5m
Assessment
Badge
**Refactoring ML/DL Algorithms: Refactor Machine Learning Algorithms**

This course explores how to select the appropriate algorithm for machine learning (ML), the principles of designing machine learning algorithms, and how to refactor machine ML code. In 11 videos, you will learn the steps involved in designing ML algorithms. The complexity in the algorithm is huge, and learners will observe how to write iterative and incremental code, and how to apply refactoring to it. This course next examines the types of ML problems, and classifies it into four categories, and how to classify machine learning algorithms. You will learn how to refactor existing ML code written in Python, and to launch and use PyCharm IDE. This course also demonstrates how to use PyCharm IDE on a specific project learners will create. You will examine the problems associated with technical debt in ML implementation, and how to manage it. Then you will learn to use SonarQube to build code coverage for machine learning code that are written in Python. Finally, this course examines automatic clone recommendations for refactoring, based on the present and the past.

11 videos |
58m
Assessment
Badge
**Final Exam: ML Engineer**

Final Exam: ML Engineer will test your knowledge and application of the topics presented throughout the ML Engineer track of the Skillsoft Aspire ML Programmer to ML Architect Journey.

1 video |
32s
Assessment
Badge
**COURSES INCLUDED**

**Applied Predictive Modeling**

In this course, you will explore machine learning predictive modeling and commonly used models like regressions, clustering, and Decision Trees that are applied in Python with the scikit-learn package. Begin this 13-video course with an overview of predictive modeling and recognize its characteristics. You will then use Python and related data analysis libraries including NumPy, Pandas, Matplotlib, and Seaborn, to perform exploratory data analysis. Next, you will examine regression methods, recognizing the key features of Linear and Logistic regressions, then apply both a linear and a logistic regression with Python. Learn about clustering methods, including the key features of hierarchical clustering and K-Means clustering, then learn how to apply hierarchical clustering and K-Means clustering with Python. Examine the key features of Decision Trees and Random Forests, then apply a Decision Tree and a Random Forest with Python. In the concluding exercise, learners will be asked to apply linear regression, logistic regression, hierarchical clustering, Decision Trees, and Random Forests with Python.

13 videos |
1h 7m
Assessment
Badge
**Implementing Deep Learning: Practical Deep Learning Using Frameworks & Tools**

Explore the concept of deep learning, including a comparison between machine learning and deep learning (ML/DL) in this 12-video course. Learners will examine the various phases of ML/DL workflows involved in building deep learning networks; recall the essential components of building and applying deep learning networks; and take a look at the prominent frameworks that can be used to simplify building ML/DL applications. You will then observe how to use the Caffe2 framework for implementing recurrent convolutional neural networks; write PyTorch code to generate images using autoencoders; and implement deep neural networks by using Python and Keras. Next, compare the prominent platforms and frameworks that can be used to simplify deep learning implementations; identify and select the best fit frameworks for prominent ML/DL use cases; and learn how to recognize challenges and strategies associated with debugging deep learning networks and algorithms. The closing exercise involves identifying the steps of ML workflow, deep learning frameworks, and strategies for debugging deep learning networks.

12 videos |
58m
Assessment
Badge
**Implementing Deep Learning: Optimized Deep Learning Applications**

This 11-video course explores the concepts of computational graphics, interfaces for programming graphics processing units (GPUs), and TensorFlow Extended and its pipeline components. Learners discover features and elements that should be considered for machine learning when building deep learning (DL) models, as well as hyperparameters that can be tuned to optimize DL models. Begin by examining the concept of computational graphs and recognize essential computational graph operations used in implementing DL. Then learn to list prominent processors with specialized purpose and architectures used in implementing DL. Recall prominent interfaces for programming GPUs with focus on Compute Unified Device Architecture (CUDA) and OpenCL, and then take a look at TensorFlow Extended (TFX) and TFX pipeline components for machine learning pipelines. Discover how to setup the TFX environment; use the ExampleGen and StatisticsGen TFX pipeline components to build pipelines; work with TensorFlow Model analysis; and explore the practical considerations for DL build and train. Finally, recall essential hyperparameters of DL algorithms that can be tuned to optimize DL models. The concluding exercise involves optimizing DL applications.

11 videos |
42m
Assessment
Badge
**Applied Deep Learning: Unsupervised Data**

This 11-video course explores the concept of deep learning and implementation of deep learning-based frameworks for natural language processing (NLP) and audio data analysis. Discover the architectures of recurrent neural network (RNN) that can be used in modeling NLP, and the challenges of unsupervised learning and the approach of using deep learning from the perspective of common unsupervised feature machine learning. First, examine the prominent statistical classification models and compare generative classifiers with discriminative classifiers; then recall different types of generative models, with focus on generative adversarial network, variational autoencoders, and flow-based generative model. Learn about setting up and working with PixelCNN; explore differences between multilayer perception (MLP), convolutional neural network (CNN), and RNN. Explore the essential capabilities and variants of ResNet that can be used for computer vision and deep learning. Finally, take a look at encoders in neural networks and compare the capabilities of standard autoencoders and variational autoencoders. The concluding exercise involves recalling RNN architecture that can be used in modeling NLP, variants of ResNet, and setting up PixelCNN.

11 videos |
1h 27m
Assessment
Badge
**Applied Deep Learning: Generative Adversarial Networks and Q-Learning**

Learners will explore variations of generative adversarial network (GAN) and the challenges associated with its models, as well as the concept of deep reinforcement learning, its application for machine learning, and how it differs from deep learning, in this 11-video course. Begin by implementing autoencoders with Keras and Python; implement GAN and the role of Generator and Discriminator; and implement GAN Discriminator and Generator with Python and Keras and build Discriminator for training models. Discover the challenges of working with GAN models and explore the concept of deep reinforcement learning and its application in the areas of robotics, finance, and health care. Compare deep reinforcement learning with deep learning, and examine challenges associated with their implementations. Learn about the basic concepts of reinforcement learning, as well as the concept of deep Q-learning and implementing deep Q-learning. Then implement deep Q-learning in Python by using Keras and OpenAI Gym. The concluding exercise involves recalling variations of GAN, implementing GAN Discriminator and Generator using Python, and implementing deep Q-learning in Python by using Keras and OpenAI Gym.

11 videos |
44m
Assessment
Badge
**Advanced Reinforcement Learning: Principles**

This 11-video course delves into machine learning reinforcement learning concepts, including terms used to formulate problems and workflows, prominent use cases and implementation examples, and algorithms. Learners begin the course by examining what reinforcement learning is and the terms used to formulate reinforcement learning problems. Next, look at the differences between machine learning and reinforcement learning by using supervised and unsupervised learning. Explore the capabilities of reinforcement learning, by looking at use cases and implementation examples. Then learners will examine reinforcement learning workflow and reinforcement learning terms; reinforcement learning algorithms and their features; and the Markov Decision Process, its variants, and the steps involved in the algorithm. Take a look at the Markov Reward Process, focusing on value functions for implementing the Markov Reward Process, and also the capabilities of the Markov Decision Process toolbox and the algorithms that are implemented within it. The concluding exercise involves recalling reinforcement learning terms, describing implementation approaches, and listing the Markov Decision Process algorithms.

11 videos |
1h 12m
Assessment
Badge
**Advanced Reinforcement Learning: Implementation**

In this 11-video course, learners can examine the role of reward and discount factors in reinforcement learning, as well as the multi-armed bandit problem and approaches to solving it for machine learning. You will begin by learning how to install the Markov Decision Policy (MDP) toolbox and implement the Discounted Markov Decision Process using the policy iteration algorithm. Next, examine the role of reward and discount factors in reinforcement learning, and the multi-armed bandit problem and solutions. Learn about dynamic programming, policy evaluation, policy iteration, value iteration, and characteristics of Bellman equation. Then learners will explore reinforcement learning agent components and applications; work with reinforcement learning agents using Keras and OpenAI Gym; describe reinforcement learning algorithms and the reinforcement learning taxonomy defined by OpenAI; and implement deep Q-learning with Keras. Finally, observe how to train deep neural networks (DNN) with reinforcement learning for time series forecasting. In the closing exercise, you will recall approaches for resolving the multi-armed bandit problem, list reinforcement learning agent components, and implement deep Q-learning by using Keras and OpenAI Gym.

11 videos |
1h 34m
Assessment
Badge
**ML/DL Best Practices: Machine Learning Workflow Best Practices**

This 12-video course explores essential phases of machine learning (ML), deep learning workflows, and data workflows that can be used to develop ML models. You will learn the best practices to build robust ML systems, and examine the challenges of debugging models. Begin the course by learning the importance of the data structure for ML accuracy and feature extraction that is wanted from the data. Next, you will learn to use checklists to develop and implement end-to-end ML and deep learning workflows and models. Learners will explore what factors to consider when debugging, and how to use flip points to debug a trained machine model. You will learn to identify and fix issues associated with training, generalizing, and optimizing ML models. This course demonstrates how to use the various phases of machine learning and data workflows that can be used to achieve key milestones of machine learning projects. Finally, you will learn high level-deep learning strategies, and the common design choices for implementing deep learning projects.

12 videos |
52m
Assessment
Badge
**ML/DL Best Practices: Building Pipelines with Applied Rules**

This course examines how to troubleshoot deep learning models, and build robust deep learning solutions. In 13 videos, learners will explore the technical challenges of managing diversified kinds of data with ML (machine learning), and how to work with its challenges. This course uses case studies to demonstrate the impact of adopting deep learning best practices, and how to deploy deep learning solutions in an enterprise. First, you will learn the best approach for architecting, building, and implementing scalable ML services, and rules to build ML pipelines into applications. Then learners will examine critical challenges and patterns associated with deploying deep learning solutions in an enterprise. You will learn to use feature engineering to apply rules and features in an application, and how to use feature engineering to manage slowed growth, training-serving skew, optimization refinement, and complex models in ML application management. Finally, you will examine the checklists that are recommended for project managers to prepare and adopt when implementing machine learning.

13 videos |
1h 3m
Assessment
Badge
**Research Topics in ML & DL**

This course explores research being done in machine learning and deep learning. Topics covered include neural networks and deep neural networks. First, learners examine how to prevent neural networks from overfitting. You will explore research on multilabel learning algorithms, multilabel classification, and multiple-output classifications, which are variants of the standard classification problem. Then examine deep learning algorithms, the enhanced performance of deeper neural networks that are more adept at automatic feature extraction. Next, ut facial alignment, regression tree ensembles, and deep features for scene recognition. Review ELM (Extreme Learning Machine), and how it is used to perform regression and multiclass classification.

13 videos |
41m
Assessment
Badge
**Deep Learning with Keras**

In this 19-video course, learners explore deep learning with Keras, including how to create and use neural networks with Keras for machine learning solutions. Begin with an overview of what neural networks are and their main components, followed by an introduction to Keras and its guiding principles. Observe how to configure Microsoft Cognitive Toolkit (CNTK) as your Keras backend; install and configure Keras; identify and work with both types of models available in Keras; and recognize features of commonly-used Keras layers and when to use them. Use Keras to make regression classifications and image classifications; Keras metrics to judge a model's performance; and Jupyter Notebooks with Keras. Next, download and load a data set from MNIST or CIFAR-10; explore data sets in Keras; prepare your data in Keras by defining input and target tensors, and compile the model in Keras. Then train and test your neural network; evaluate and score the performance of neural networks in Keras, and make predictions using your data set in Keras. The closing exercise involves using a neural network to make predictions.

19 videos |
1h 54m
Assessment
Badge
**Final Exam: ML Architect**

Final Exam: ML Architect will test your knowledge and application of the topics presented throughout the ML Architect track of the Skillsoft Aspire ML Programmer to ML Architect Journey.

1 video |
32s
Assessment
Badge
**EARN A DIGITAL BADGE WHEN YOU COMPLETE THESE TRACKS**

Skillsoft is providing you the opportunity to earn a digital badge upon successful completion on some of our courses, which can be shared on any social network or business platform.

**Digital badges are yours to keep, forever.**