2
Neural Networks
In Chapter 1, we introduced a number of basic machine learning (ML) concepts and techniques. We went through the main ML paradigms, as well as some popular classic ML algorithms, and we finished on neural networks (NN). In this chapter, we will formally introduce what NNs are, discuss their mathematical foundations, describe in detail how their building blocks work, see how we can stack many layers to create a deep feedforward NN, and then learn how to train them.
In this chapter, we will cover the following main topics:
- The need for NNs
- The math of NNs
- An introduction to NNs
- Training NNs
The link between NNs and the human brain
Initially, NNs were inspired by the biological brain (hence the name). Over time, however, we’ve stopped trying to emulate how the brain works, and instead, we’re focused on finding the correct configurations for specific tasks, including computer vision, natural language processing, and speech...
