This repo is home to notes & the code that accompanies Andrew W. Trask's "Grokking Deep Learning" book. It provides a solid foundation in deep learning so that you can master any major deep learning framework.
The book requires no math background beyond basic arithmetic. It doesn't rely on a high-level library that might hide what's going on. Anyone can read the book and understand how deep learning really works. You won't just read the theory, you'll discover it yourself.
(You can Buy the Book from Manning Publications or Amazon).
"Grokking Deep Learning" has 16 chapters. We provide links for the available notebooks:
- Introducing Deep Learning: Why you should Learn It?
- fundamental Concepts: How Do Machines Learn?
- Introduction to Neural Learning: Forward Propagation
- Introduction to Neural Learning: Gradient Descent
- Learning Multiple Weights at a Time: Generalizing Gradient Descent
- Building your first deep neural network: Introduction to Backpropagation
- How to Picture Neural Networks: In your Head & on Paper
- Learning Signal & Ignoring Noise: Introduction to Regularization & Batching
- Modeling Probabilities & Non-Linearities: Activation Functions
- Neural Learning about Edges & Corners: Introduction to Convolutional Neural Networks
- Neural Networks that Understand Language: King - Man + Woman == ?
- Neural Networks that write like Shakespeare: Recurrent Layers for Variable Length Data
- Introducing Automatic Optimization: Let's build a deep learning framework
- Learning to Write like Shakespeare: Long Short-term Memory
- Deep Learning on Unseen Data: Introducing Federated Learning
- Where to Go from Here: A brief Guide
Hidden Notebooks are mostly based on original content from the book.