MATRIX EQUATIONS IN DEEP LEARNING RESOLUTION FOR M DATA HAS N PARAMETERS

Abstract

This article on the vectorization of learning equations by neural network aims to give the matrix equations on [1-3]: first on the Z [8, 9] model of the perceptron[6] which calculates the inputs X, the Weights W and the bias, second on the quantization function [10] [11], called loss function [6, 7] [8]. and finally thegradient descent algorithm for maximizing likelihood and minimizing Z errors [4, 5].