Improving Neural Networks: Data Scaling & Regularization

Neural Networks
  • 10 Videos | 1h 41m 10s
  • Includes Assessment
  • Earns a Badge
Likes 5 Likes 5
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.

WHAT YOU WILL LEARN

  • discover the key concepts covered in this course
    describe the approach of creating deep learning network models along with the steps involved in optimizing the networks
    implement the learning rate adaptation schedule in Keras using SGD and specifying learning rate, epoch and decay
    describe the concept of scaling data and list the prominent data scaling methods
    describe the concept of batch normalization and internal covariate shift
  • demonstrate how to implement batch normalization using Python and TensorFlow
    implement L1 regularization to manage overfitting problems
    implement L2 regularization to manage overfitting problems
    demonstrate how to implement gradient descent using Python
    recall the prominent data scaling methods, implement L1 regularization and gradient descent using Python

IN THIS COURSE

  • Playable
    1. 
    Course Overview
    1m 16s
    UP NEXT
  • Playable
    2. 
    Optimizing Networks
    7m 48s
  • Locked
    3. 
    Rate Adaption Schedule Implementation with Keras
    7m 22s
  • Locked
    4. 
    Scaling and Scaling Methods
    4m 36s
  • Locked
    5. 
    Batch Normalization and Internal Covariate Shift
    7m 9s
  • Locked
    6. 
    Implementing Batch Normalization
    8m 16s
  • Locked
    7. 
    Implementing L1 Regularization
    17m 56s
  • Locked
    8. 
    Implementing L2 Regularization
    9m 33s
  • Locked
    9. 
    Implementing Gradient Descent
    13m 26s
  • Locked
    10. 
    Exercise: L1 Regularization and Gradient Descent
    19m 48s

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.

YOU MIGHT ALSO LIKE