Free online book “Neural Networks” by Genevieve Orr. It’s goal is to introduce students to a powerful class of model, the Neural Network, a broad term which includes many diverse models and approaches. It will first motivate networks by analogy to the brain. The analogy is loose, but serves to introduce the idea of parallel and distributed computation.
Book Description
It then introduces one kind of network in detail: the feedforward network trained by backpropagation of error. It discusses model architectures, training methods and data representation issues. It covers everything you need to know to get back propagation working for you. A range of applications and extensions to the basic model will be presented in the final section of the module.
Table of Contents
- Introduction
- Classification
- Optimizing Linear Networks
- The Backprop Toolbox
- Unsupervised Learning
- Reinforcement Learning
- Advanced Topics