9 Artificial neural networks

 

This chapter covers

  • Understanding the inspiration and intuition of artificial neural networks
  • Identifying problems that can be solved with artificial neural networks
  • Understanding and implementing forward propagation using a trained network
  • Understanding and implementing backpropagation to train a network
  • Designing artificial neural network architectures to tackle different problems

What are artificial neural networks?

Artificial neural networks (ANNs) are powerful tools in the machine learning toolkit, used in a variety of ways to accomplish objectives such as image recognition, natural language processing, and game playing. ANNs learn in a similar way to other machine learning algorithms: by using training data. They are best suited to unstructured data where it’s difficult to understand how features relate to one another. This chapter covers the inspiration of ANNs; it also shows how the algorithm works and how ANNs are designed to solve different problems.

The Perceptron: A representation of a neuron

Defining artificial neural networks

Forward propagation: Using a trained ANN

Backpropagation: Training an ANN

Phase A: Setup

Phase B: Forward propagation

Phase C: Training

Options for activation functions

Designing artificial neural networks

Inputs and outputs

Hidden layers and nodes

Weights

Bias

Activation functions

Cost function and learning rate

Artificial neural network types and use cases

Convolutional neural network

Recurrent neural network

Generative adversarial network

Summary of artificial neural networks