ALF -- A Fitness-Based Artificial Life Form for Evolving Large-Scale Neural Networks

TL;DR

This paper introduces ALF, a novel genetic algorithm for evolving large-scale neural networks that improves efficiency and convergence through speciation, dynamic adaptation, and integrated solution quality.

Contribution

ALF is a new TWEANN algorithm that enhances evolution of neural network topologies by incorporating speciation, adaptive strategies, and solution quality into the evolutionary process.

Findings

ALF enables faster evolution of large-scale neural networks.

Evolved ANNs are more efficient and better suited for large problems.

Experiments demonstrate improved convergence and solution quality.

Abstract

Machine Learning (ML) is becoming increasingly important in daily life. In this context, Artificial Neural Networks (ANNs) are a popular approach within ML methods to realize an artificial intelligence. Usually, the topology of ANNs is predetermined. However, there are problems where it is difficult to find a suitable topology. Therefore, Topology and Weight Evolving Artificial Neural Network (TWEANN) algorithms have been developed that can find ANN topologies and weights using genetic algorithms. A well-known downside for large-scale problems is that TWEANN algorithms often evolve inefficient ANNs and require long runtimes. To address this issue, we propose a new TWEANN algorithm called Artificial Life Form (ALF) with the following technical advancements: (1) speciation via structural and semantic similarity to form better candidate solutions, (2) dynamic adaptation of the observed candidate solutions for better convergence properties, and (3) integration of solution quality into genetic reproduction to increase the probability of optimization success. Experiments on large-scale ML problems confirm that these approaches allow the fast solving of these problems and lead to efficient evolved ANNs.