initialize_weights: Initialize MLP Weights

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

Initialize MLP Weights

Description

Creates a numeric vector of randomly initialized weights and bias terms for an MLP architecture.

Usage

initialize_weights(
  architecture,
  input_dim = NULL,
  method = c("uniform", "normal"),
  lower = -0.5,
  upper = 0.5,
  mean = 0,
  sd = 0.1,
  seed = NULL
)

Arguments

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.
method	Initialization method. Currently "uniform" and "normal" are supported.
lower	Lower bound for uniform initialization.
upper	Upper bound for uniform initialization.
mean	Mean for normal initialization.
sd	Standard deviation for normal initialization.
seed	Optional random seed.

Value

A numeric vector containing initialized parameters.

Examples

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

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