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

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...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-04
Main Authors: Krauss, Rune, Merten, Marcel, Bockholt, Mirco, Drechsler, Rolf
Format: Article
Language:English
Subjects:
Algorithms
Artificial intelligence
Artificial neural networks
Evolution
Genetic algorithms
Learning theory
Machine learning
Network topologies
Neural networks
Optimization
Speciation
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422
DOI:10.48550/arxiv.2104.08252