Deep Learning-Based Operators for Evolutionary Algorithms

Autor:	Shem-Tov, Eliad, Sipper, Moshe, Elyasaf, Achiya
Rok vydání:	2024
Předmět:	Computer Science - Neural and Evolutionary Computing Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: 16 pages, 7 figures, 2 tables. Accepted to Genetic Programming Theory & Practice XXI (GPTP 2024). arXiv admin note: text overlap with arXiv:2403.11159
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2407.10477 Zobrazit plný text záznamu View this record from Arxiv