Deep Learning-Based Operators for Evolutionary Algorithms

2024/07/15 by Eliad Shem-Tov, Moshe Sipper, Shem-Tov, Eliad +3
Computer Science · #Metaheuristic Optimization Algorithms Research #Evolutionary Algorithms and Applications

paper · pdf · doi:10.48550/arxiv.2407.10477

Abstract

We present two novel domain-independent genetic operators that harness the capabilities of deep learning: a crossover operator for genetic algorithms and a mutation operator for genetic programming. Deep Neural Crossover leverages the capabilities of deep reinforcement learning and an encoder-decoder architecture to select offspring genes. BERT mutation masks multiple gp-tree nodes and then tries to replace these masks with nodes that will most likely improve the individual's fitness. We show the efficacy of both operators through experimentation.

Related

• Structured mutation inspired by evolutionary theory enriches population performance and diversity
• Learning to Generate Genotypes with Neural Networks
• IE-GAN: An Improved Evolutionary Generative Adversarial Network Using a New Fitness Function and a Generic Crossover Operator
• Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
• Safe Mutations for Deep and Recurrent Neural Networks through Output Gradients