- author = "Eliad Shem-Tov and Moshe Sipper and Achiya Elyasa",
- title = "Deep Learning-Based Operators for Evolutionary Algorithms",
- booktitle = "Genetic Programming Theory and Practice XXI",
- year = "2024",
- editor = "Stephan M. Winkler and Wolfgang Banzhaf and Ting Hu and Alexander Lalejini",
- series = "Genetic and Evolutionary Computation",
- pages = "51--66",
- address = "University of Michigan, USA",
- month = jun # " 6-8",
- publisher = "Springer",
- keywords = "genetic algorithms, genetic programming, AI, ANN",
- isbn13 = "978-981-96-0076-2",
-
URL = "
https://arxiv.org/abs/2407.10477",
-
DOI = "
doi:10.1007/978-981-96-0077-9_3",
- size = "16 pages",
- 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 fitness. We show the efficacy of both operators through experimentation.",
-
notes = "See 2021 MSc
https://primo.bgu.ac.il/discovery/delivery/972BGU_INST:972BGU/12238956030004361
alma9926802146404361
Published in 2025 after the workshop",
