Hands-On Keras for Machine Learning Engineers

Video description

Learn to design and build deep learning models with Keras

About This Video

  • Learn how to use more advanced techniques required to develop state-of-the-art deep learning models
  • Learn how to use advanced image augmentation techniques in order to lift model performance
  • Learn how to enhance performance with learning rate schedules

In Detail

Welcome to hands-on Keras for machine learning engineers. This is a carefully structured course to guide you in your journey to learn deep learning in Python with Keras. Discover the Keras Python library for deep learning and learn the process of developing and evaluating deep learning models using it.

There are two top numerical platforms for developing deep learning models; they are Theano, developed by the University of Montreal, and TensorFlow developed at Google. Both were developed for use in Python and both can be leveraged by the super-simple-to-use Keras library. Keras wraps the numerical computing complexity of Theano and TensorFlow, providing a concise API that we will use to develop our own neural network and deep learning models. Keras has become the gold standard in the applied space for rapid prototyping deep learning models.

This course is a hands-on guide. It is a playbook and a workbook intended for you to learn by doing and then apply your new understanding to your own deep learning Keras models.

Who this book is for

This course is for developers, machine learning engineers, and data scientists that want to learn how to get the most out of Keras. You do not need to be a machine learning expert, but it would be helpful if you knew how to navigate a small machine learning problem using SciKit-Learn. Basic concepts such as cross-validation and one-hot encoding used in lessons and projects are described, but only briefly. With all of this in mind, this is an entry-level course on the Keras library.

Publisher resources

Download Example Code

Table of contents

  1. Chapter 1 : Introduction
    1. Introduction
    2. What You'll Learn in this Course
    3. Is this Course Right for You?
    4. What is Keras?
  2. Chapter 2 : Foundations
    1. Theano
    2. TensorFlow
    3. Artificial Neural Network Anatomy
    4. Deep Learning
    5. Keras Life Cycle
    6. Keras Code Anatomy
    7. Demo: Case Study on Pima Indian Diabetes Dataset: Load Data
    8. Demo: Case Study on Pima Indian Diabetes Dataset: Define and Compile
    9. Demo: Case Study on Pima Indian Diabetes Dataset: Fit and Evaluate
    10. Performance Evaluation on Neural Networks
    11. Demo: Case Study on Data Segmentation
    12. Scikit-Learn for General Machine Learning
    13. Evaluate Models with Cross-Validation
    14. Grid Search Deep Learning Model Parameters
    15. Demo: Case Study on Multiclass Classification
    16. Demo: Case Study on Multiclass Classification: Part 2
    17. Demo: Case Study on Binary Classification
    18. Demo: Case Study on Binary Classification: Part 2
    19. Demo: Case Study on Binary Classification: Part 3
    20. Demo: Case Study on Binary Classification: Part 4
    21. Demo: Case Study on Regression
    22. Demo: Case Study on Regression: Part 2
    23. Demo: Case Study on Regression: Part 3
  3. Chapter 3 : Going Deeper with Keras
    1. Model Serialization
    2. Save Neural Network to JSON
    3. Save Neural Network to YAML
    4. Demo: Case Study on Checkpointing
    5. Demo: Case Study on Checkpointing: Part 2
    6. Plotting History
    7. Visualize Model Training History in Keras
    8. Demo: Case Study on Dropping Out
    9. Demo: Case Study on Dropping Out: Part 2
    10. Dropout Tips
    11. Learning Rate Defined
    12. Configure Learning Rate
    13. Demo: Case Study on Learning Rates
    14. Demo: Case Study on Learning Rates: Part 2
    15. Demo: Case Study on Learning Rates: Part 3
  4. Chapter 4 : Convolutional Neural Networks
    1. Convolutional Neural Networks
    2. Demo: Case Study on Handwritten Digit Recognition
    3. Demo: Case Study Handwritten Digit Recognition: Part 2
    4. Demo: Case Study on Handwritten Digit Recognition: Part 3
    5. Demo: Case Study on Handwritten Digit Recognition: Part 4
    6. Image Augmentation
    7. Demo: Case Study on Image Augmentation
    8. Demo: Case Study on Image Augmentation: Part 2
    9. Image Augmentation Tips
    10. Object Recognition
    11. Demo: Case Study on Object Recognition
    12. Improving Model Performance
    13. Sentiment Analysis in Keras
    14. IMDB Dataset Properties
    15. Word Embedding Defined
    16. Demo: Case Study on Word Embedding
    17. Demo: Case Study on Word Embedding: Part 2
  5. Chapter 5 : Recurrent Neural Networks
    1. Recurrent Neural Networks
    2. Demo: Case Study on Time Series Prediction
    3. Demo: Case Study on Time Series Prediction: Part 2
    4. Demo: Case Study on Time Series Prediction: Part 3
    5. Demo: Case Study on Time Series Prediction with LSTM
    6. Demo: Case Study on Time Series Prediction with LSTM: Part 2
    7. Demo: Case Study on Time Series Prediction with LSTM: Part 3
    8. Demo: Case Study on Sequence Classification
    9. Demo: Case Study on Sequence Classification: Part 2

Product information

  • Title: Hands-On Keras for Machine Learning Engineers
  • Author(s): Mike West
  • Release date: November 2021
  • Publisher(s): Packt Publishing
  • ISBN: 9781803232522