Chapter 7. Fairly simple neural networks

 

When we hear about advances in artificial intelligence these days, in the late 2010s, they generally concern a particular subdiscipline known as machine learning (computers learning some new information without being explicitly told it). More often than not those advances are being driven by a particular machine-learning technique known as neural networks. Although invented decades ago, neural networks have been going through a kind of renaissance as improved hardware and newly discovered research-driven software techniques enable a new paradigm known as deep learning.

Deep learning has turned out to be a broadly applicable technique. It has been found useful in everything from hedge-fund algorithms to bioinformatics. Two deep-learning applications that consumers have become familiar with are image recognition and speech recognition. If you have ever asked your digital assistant what the weather is or had a photo program recognize your face, there was probably some deep learning going on.

7.1. Biological basis?

7.2. Artificial neural networks

7.3. Preliminaries

7.4. Building the network

7.5. Classification problems

7.6. Speeding up neural networks

7.7. Neural network problems and extensions

7.8. Real-world applications

7.9. Exercises