Simultaneous Optimization of Neural Network Weights and Active Nodes using Metaheuristics

TL;DR

This paper introduces a metaheuristic framework for optimizing neural network weights and transfer function parameters simultaneously, demonstrating that adaptive transfer functions combined with Artificial Bee Colony optimization yield superior classification accuracy.

Contribution

It proposes a novel combined genotype representation for joint optimization of weights and transfer functions in neural networks, with comprehensive analysis comparing different transfer functions and algorithms.

Findings

Adaptive transfer functions improve neural network performance.

Artificial Bee Colony outperforms other algorithms like PSO and DE.

Optimized heterogeneity enhances classification accuracy.

Abstract

Optimization of neural network (NN) significantly influenced by the transfer function used in its active nodes. It has been observed that the homogeneity in the activation nodes does not provide the best solution. Therefore, the customizable transfer functions whose underlying parameters are subjected to optimization were used to provide heterogeneity to NN. For the experimental purpose, a meta-heuristic framework using a combined genotype representation of connection weights and transfer function parameter was used. The performance of adaptive Logistic, Tangent-hyperbolic, Gaussian and Beta functions were analyzed. In present research work, concise comparisons between different transfer function and between the NN optimization algorithms are presented. The comprehensive analysis of the results obtained over the benchmark dataset suggests that the Artificial Bee Colony with adaptive transfer function provides the best results in terms of classification accuracy over the particle swarm optimization and differential evolution.