Adapted version of companion Jupyter notebooks for the book "Deep Learning with Python"

This repository contains Jupyter notebooks implementing the code samples found in the book Deep Learning with Python, 2nd Edition (Manning Publications). Metropolia University of Applied Sciences has access to read this book through library services.

The notebooks are adapted for the course Neural Networks for Machine Learning Applications taught at Metropolia University of Applied Sciences, Helsinki, Finland. The original notebooks are edited to suit better for the course structure and syllabus. (For readability, these notebooks only contain runnable code blocks and section titles, and omit everything else in the book: text paragraphs, figures, and pseudocode.)

As the original author wrote, it is highly recommended reading the notebooks side by side with your copy of the book.

These notebooks use TensorFlow 2.6.

Table of contents

• Chapter 2: The mathematical building blocks of neural networks
• Chapter 3: Introduction to Keras and TensorFlow
• Chapter 4: Getting started with neural networks: classification and regression
• Chapter 5: Fundamentals of machine learning
• Chapter 7: Working with Keras: a deep dive
• Chapter 8: Introduction to deep learning for computer vision
• Chapter 9: Advanced deep learning for computer vision
  • Part 1: Image segmentation
  • Part 2: Modern convnet architecture patterns
  • Part 3: Interpreting what convnets learn
• Chapter 10: Deep learning for timeseries
• Chapter 11: Deep learning for text
  • Part 1: Introduction
  • Part 2: Sequence models
  • Part 3: Transformer
  • Part 4: Sequence-to-sequence learning
• Chapter 12: Generative deep learning
  • Part 1: Text generation
  • Part 2: Deep Dream
  • Part 3: Neural style transfer
  • Part 4: Variational autoencoders
  • Part 5: Generative adversarial networks
• Chapter 13: Best practices for the real world
• Chapter 14: Conclusions