decode_weights: Decode an MLP Weight Vector

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

Decode an MLP Weight Vector

Description

Converts a numeric parameter vector into layer-wise weight matrices and bias vectors.

Usage

decode_weights(weights, architecture, input_dim = NULL)

Arguments

weights	A numeric vector of MLP parameters.
architecture	An object created by mlp_architecture().
input_dim	Optional positive integer specifying the number of input features. If NULL, architecture$input_dim is used.

Value

A list containing layer-wise weight matrices and bias vectors.

Examples

arch <- mlp_architecture(
  input_dim = 2,
  layers = list(dense_layer(3), dense_layer(1, activation = "linear"))
)
w <- initialize_weights(arch, seed = 123)
decoded <- decode_weights(w, arch)

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