Chapter 9. Artificial Neural Networks
The popularity of neural networks surged in the 90s. They were seen as the silver bullet to a vast number of problems. At its core, a neural network is a nonlinear statistical model that leverages the logistic regression to create a nonlinear distributed model. The concept of artificial neural networks is rooted in biology, with the desire to simulate key functions of the brain and replicate its structure in terms of neurons, activation, and synapses.
In this chapter, you will move beyond the hype and learn:
- The concept and elements of the multilayer perceptron (MLP)
- How to train a neural network using error backpropagation
- The evaluation and tuning of MLP configuration parameters
- Full Scala implementation of the MLP classifier
- How to apply MLP to extract correlation models for currency exchange rates
