Index matrix interpretation of the Multilayer perceptron

Abstract

Neural networks are a mathematical model for solving problems, that uses the structure of human brain. One of the mostly used kinds of neural networks, the Multilayer perceptron (MLP), has been modelled with various tools. Here, starting with the MLP, we approach the problem by modelling neural networks in terms of index matrices (IMs). The work includes IM interpretations of the building components of the neural network, namely, input vector, weight coefficients, transfer function, and biases, as well as the various operations defined over these.