mlp_crossentropy_gradient: Compute Multi-Class Cross-Entropy Gradient for an MLP

In metANN: Metaheuristic and Gradient-Based Optimization for Neural Network Training and Continuous Problems

Compute Multi-Class Cross-Entropy Gradient for an MLP

Description

Internal helper for computing the gradient of softmax cross-entropy loss with respect to the MLP parameter vector.

Usage

mlp_crossentropy_gradient(x, y, weights, architecture, epsilon = 1e-15)

Arguments

x	Numeric input matrix.
y	Numeric one-hot encoded response matrix.
weights	Numeric parameter vector.
architecture	MLP architecture object.
epsilon	Small value used for numerical stability.

Value

A list containing loss, predictions, and gradient vector.

metANN documentation built on May 16, 2026, 1:06 a.m.