Building Neural Networks: Artificial Neural Networks Using Frameworks
Overview/Description
Expected Duration
Lesson Objectives
Course Number
Expertise Level
Overview/Description
Discover how to implement various neural networks scenarios using Python, Keras, and TensorFlow. How to optimize, tune, and speed up the processes of artificial neural networks and how to implement predictions with ANN is also covered.

Expected Duration (hours)
1.9

Lesson Objectives Building Neural Networks: Artificial Neural Networks Using Frameworks

identify the key subject areas covered in this course
list the prominent building blocks involved in building a neural network
recall the concept and characteristics of evolutionary algorithms, gradient descent, and genetic algorithms
build neural networks using Python and Keras for classification with Tensorflow as the backend
build neural networks using PyTorch
implement object image classification using neural network algorithms
define and illustrate the use of learning rates to optimize deep learning
describe the various parameters and approaches of optimizing neural network speed
demonstrate how to select hyperparameters and tune for dense networks using Hyperas
build linear models with estimators using the capabilities of TensorFlow
specify approaches that can be used to implement predictions with neural networks
describe the temporal and heterogenous approaches of optimizing predictions
build a neural network using Python and Keras, tune dense networks using Hyperas, and build a linear model with TensorFlow

Course Number: it_mlbdnndj_02_enus

Expertise Level
Intermediate