Training Neural Networks: Advanced Learning Algorithms

Neural Networks    |    Intermediate
  • 15 Videos | 1h 47m 6s
  • Includes Assessment
  • Earns a Badge
Likes 7 Likes 7
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

  • Playable
    1. 
    Course Overview
    1m 59s
    UP NEXT
  • Playable
    2. 
    Online and Offline Learning
    6m 15s
  • Locked
    3. 
    Training Patterns and Teaching Input
    8m 42s
  • Locked
    4. 
    Training Samples
    9m 3s
  • Locked
    5. 
    Baseline Overfitting and Underfitting
    9m 17s
  • Locked
    6. 
    L1 and L2 Regularization
    6m 2s
  • Locked
    7. 
    Training Neural Networks
    5m 24s
  • Locked
    8. 
    Pattern Association Training Algorithms
    5m 13s
  • Locked
    9. 
    Learning Vector Quantization
    7m 39s
  • Locked
    10. 
    Modified Hebbian Learning
    4m 57s
  • Locked
    11. 
    Hebbian Learning Rule
    5m 45s
  • Locked
    12. 
    Competitive Learning
    7m 43s
  • Locked
    13. 
    Optimizing Neural Networks
    7m 40s
  • Locked
    14. 
    Debugging Neural Networks
    7m 13s
  • Locked
    15. 
    Exercise: Implement Advanced Algorithms
    7m 44s

EARN A DIGITAL BADGE WHEN YOU COMPLETE THIS COURSE

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

Digital badges are yours to keep, forever.