This module explains how to build up a basic neural network step-by-step. It also uses the MNIST dataset for detecting numbers from handwriting.

Neural Networks: Beginners to Advanced

Machine learning is one of the fastest growing fields. This module aims to teach one of the fundamental concepts of machine learning, that is neural networks. You will learn the basic concepts of building a model as well as the mathematical explanation behind the neural network. You will learn to build the neural network from scratch, in Python. You will also learn how to train and optimize your network to achieve a better result. We’ve specifically designed this module for beginners so it doesn’t require any prior programming experience. Happy learning!

Make Your Own Neural Network in Python

Looking back over this work, we’ve created a neural network using only the simple concepts we covered earlier and implementing them using simple Python.

This neural network has performed really well, without any extra fancy mathematics. Its performance is very respectable compared to the networks that academics and researchers make.

Try to experiment further with the neural network we’ve already made—try a different number of hidden nodes, or a different scaling, or even a different activation function, just to see what happens.

## Final code


Looking back over this work, we’ve created a neural network using only the simple concepts we covered earlier and implementing them using simple Python.

This neural network has performed really well, without any extra fancy mathematics. Its performance is very respectable compared to the networks that academics and researchers make.

Try to experiment further with the neural network we’ve already made—try a different number of hidden nodes, or a different scaling, or even a different activation function, just to see what happens.

# Final code


Look at the final code for a three-layer neural network for learning the MNIST dataset.

Prologue

Part 1 - A Little Background

Part 2 - Let's Get Started!

Part 3 - Backward Propagation of Error

Part 4 - Adjusting the Link Weights

Part 5 - A Gentle Start with Python

Part 6 - Neural Network with Python

Part 7 - Testing Neural Network against MNIST Dataset

Part 8 - Some Suggested Improvements

Part 9 - Even More Fun!

Appendix: A Small Guide to Calculus

Conclusion