Learning to Generate Genotypes with Neural Networks
This work addresses the challenge of improving evolutionary algorithms for discrete optimization problems, offering a novel method that could enhance performance in domains like combinatorial optimization.
The paper tackled the problem of using neural networks to provide mutation distributions for evolutionary algorithms, showing that this approach can solve difficult discrete problems like MaxSat and HIFF and often outperforms other evolutionary techniques.
Neural networks and evolutionary computation have a rich intertwined history. They most commonly appear together when an evolutionary algorithm optimises the parameters and topology of a neural network for reinforcement learning problems, or when a neural network is applied as a surrogate fitness function to aid the evolutionary optimisation of expensive fitness functions. In this paper we take a different approach, asking the question of whether a neural network can be used to provide a mutation distribution for an evolutionary algorithm, and what advantages this approach may offer? Two modern neural network models are investigated, a Denoising Autoencoder modified to produce stochastic outputs and the Neural Autoregressive Distribution Estimator. Results show that the neural network approach to learning genotypes is able to solve many difficult discrete problems, such as MaxSat and HIFF, and regularly outperforms other evolutionary techniques.