Make Your Own Neural Network

Learn the fundamentals of neural networks and deep learning through hands-on coding and simple mathematics

Author: Tariq Rashid

Year: 2023

Summary:

Intro

A step-by-step gentle journey through the mathematics of neural networks, and making your own using the Python computer language.

Neural networks are a key element of deep learning and artificial intelligence, which today is capable of some truly impressive feats. Yet too few really understand how neural networks actually work.

This guide will take you on a fun and unhurried journey, starting from very simple ideas, and gradually building up an understanding of how neural networks work. You won't need any mathematics beyond secondary school, and an accessible introduction to calculus is also included.

The ambition of this guide is to make neural networks as accessible as possible to as many readers as possible — there are enough texts for advanced readers already!

You'll learn to code in Python and make your own neural network, teaching it to recognise human handwritten numbers, and performing as well as professionally developed networks.

Part 1: The Core Ideas

Part 1 focuses on the fundamental mathematical ideas behind neural networks. It introduces concepts with clear illustrations and real-world examples, making abstract ideas like weights, activation functions, and training simple to grasp.

Part 2: Hands-On Learning with Python

Part 2 provides a practical introduction to the Python programming language. You'll build a neural network step by step, learning how it can be trained to recognize handwritten digits and achieve performance comparable to professionally developed models.

Part 3: Advanced Applications and Real-World Testing

Part 3 pushes the performance of your neural network to industry-leading levels — reaching 98% accuracy — using only simple code and basic principles. You'll test the network on your own handwriting, explore how it makes decisions internally, and even run it on a Raspberry Pi Zero, bringing AI to the edge of your home computing devices.