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

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