Machine Learning with Apache Spark Quick Start Guide

Multilayer perceptrons

A single-layer perceptron (SLP) is a basic type of ANN that consists of just two layers of nodes—an input layer containing input nodes and an output layer containing output nodes. A multilayer perceptron (MLP), however, introduces one or more hidden layers between the input and output layers, giving them the ability to learn nonlinear functions, as illustrated in Figure 7.1:

Figure 7.1: Multilayer perceptron neural architecture