Deep Learning-Based Operators for Evolutionary Algorithms
This work addresses the challenge of enhancing evolutionary algorithms for researchers and practitioners in optimization, though it appears incremental as it builds on existing methods with deep learning integration.
The authors tackled the problem of improving evolutionary algorithms by introducing two novel domain-independent genetic operators that utilize deep learning: a crossover operator for genetic algorithms and a mutation operator for genetic programming, resulting in demonstrated efficacy through experimentation.
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.