Artificial Neural Networks: Table of Contents

In this blog, we are going to be diving into the mathematics, theory, and implementation of Neural Network technology. All of our implementations will be done in Python (I am using 3.6) and use exclusively NumPy (although numpy operations and data types can be easily replaced by GPU supported python linear algebra packages such as PyTorch).

Feel free to skip to the sections that interest you most, you can always go back to a previous section!

1. Background

• 1.a What is an Artificial Neural Network?
• 1.b Activation Functions and Their Gradients
• 1.c Loss Functions and Their Gradients

2. Dense Networks

• 2.a Feedforward Networks
• 2.b Convolutional Networks

3. Time-series Networks

• 3.a Principles Behind Recurrent Networks

4. Tree & Graph Networks

• 4.a Processing Tree Data
• 4.b Processing Graph Data

5. Varients & Additions

• 5.a Attention
• 5.b Neural Turing Machines

6. Bayesian Neural Networks