Training Neural Networks: Advanced Learning Algorithms

Neural Networks    |    Intermediate
  • 15 videos | 1h 40m 36s
  • Includes Assessment
  • Earns a Badge
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.

WHAT YOU WILL LEARN

  • Identify the subject areas covered in this course
    Describe features of online and offline training methods in artificial neural network
    Describe the training patterns and teaching inputs that are used in artificial neural networks
    Describe the approach of managing training samples
    Implement overfitting and underfitting using baseline model
    Describe the regularization techniques used in deep neural network
    Train built models of neural networks using python to implement prediction with high accuracy
    List the prominent training algorithms that are used for pattern association
  • Describe the architecture along with the algorithm associated with learning vector quantization
    Define the essential phases involved in implementing hebbian learning
    Implement the hebbian learning rule using python
    Describe the steps involved in implementing competitive learning
    List approaches of optimizing neural networks
    Debug neural networks
    Recall the training algorithms used for pattern association, list the steps of implementing competitive learning, and implement the hebbian learning rule using python

IN THIS COURSE

  • 1m 59s
  • 6m 15s
    Upon completion of this video, you will be able to describe features of online and offline training methods for artificial neural networks. FREE ACCESS
  • Locked
    3.  Training Patterns and Teaching Input
    8m 42s
    After completing this video, you will be able to describe the training patterns and teaching inputs used in artificial neural networks. FREE ACCESS
  • Locked
    4.  Training Samples
    9m 3s
    Upon completion of this video, you will be able to describe the approach of managing training samples. FREE ACCESS
  • Locked
    5.  Baseline Overfitting and Underfitting
    9m 17s
    In this video, you will learn how to implement overfitting and underfitting using a baseline model. FREE ACCESS
  • Locked
    6.  L1 and L2 Regularization
    6m 2s
    Upon completion of this video, you will be able to describe the regularization techniques used in deep neural networks. FREE ACCESS
  • Locked
    7.  Training Neural Networks
    5m 24s
    In this video, learn how to train models of neural networks using Python to implement prediction with high accuracy. FREE ACCESS
  • Locked
    8.  Pattern Association Training Algorithms
    5m 13s
    Upon completion of this video, you will be able to list the prominent training algorithms that are used for pattern association. FREE ACCESS
  • Locked
    9.  Learning Vector Quantization
    7m 39s
    After completing this video, you will be able to describe the architecture and the algorithm associated with learning vector quantization. FREE ACCESS
  • Locked
    10.  Modified Hebbian Learning
    4m 57s
    In this video, learn how to define the essential phases involved in implementing Hebbian learning. FREE ACCESS
  • Locked
    11.  Hebbian Learning Rule
    5m 45s
    Find out how to implement the Hebbian learning rule using Python. FREE ACCESS
  • Locked
    12.  Competitive Learning
    7m 43s
    Upon completion of this video, you will be able to describe the steps involved in implementing competitive learning. FREE ACCESS
  • Locked
    13.  Optimizing Neural Networks
    7m 40s
    Upon completion of this video, you will be able to list approaches for optimizing neural networks. FREE ACCESS
  • Locked
    14.  Debugging Neural Networks
    7m 13s
    In this video, you will learn how to debug neural networks. FREE ACCESS
  • Locked
    15.  Exercise: Implement Advanced Algorithms
    7m 44s
    Upon completion of this video, you will be able to recall the training algorithms used for pattern association, list the steps of implementing competitive learning, and implement the Hebbian learning rule using Python. FREE ACCESS

EARN A DIGITAL BADGE WHEN YOU COMPLETE THIS COURSE

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.

YOU MIGHT ALSO LIKE

Course Neural Network Mathematics: Exploring the Math behind Gradient Descent
Course Building Neural Networks: Development Principles
Course Convolutional Neural Networks: Implementing & Training

PEOPLE WHO VIEWED THIS ALSO VIEWED THESE

Course Deep Learning with Keras
Course Using BigML: An Introduction to Machine Learning & BigML
Course Building Neural Networks: Artificial Neural Networks Using Frameworks