Epigenetic evolution of deep convolutional models

TL;DR

This paper introduces an enhanced neuroevolution framework for deep convolutional networks that evolves layer configurations and kernel shapes, combining structural evolution with backpropagation to improve image classification performance.

Contribution

It extends neuroevolution methods to layered networks with variable kernel shapes, integrating structural and weight optimization in a hybrid framework.

Findings

Crossover operator produces better offspring even with limited training data.

Evolved networks outperform baseline models on image classification benchmarks.

Flexible kernel layouts improve network adaptability and performance.

Abstract

In this study, we build upon a previously proposed neuroevolution framework to evolve deep convolutional models. Specifically, the genome encoding and the crossover operator are extended to make them applicable to layered networks. We also propose a convolutional layer layout which allows kernels of different shapes and sizes to coexist within the same layer, and present an argument as to why this may be beneficial. The proposed layout enables the size and shape of individual kernels within a convolutional layer to be evolved with a corresponding new mutation operator. The proposed framework employs a hybrid optimisation strategy involving structural changes through epigenetic evolution and weight update through backpropagation in a population-based setting. Experiments on several image classification benchmarks demonstrate that the crossover operator is sufficiently robust to produce increasingly performant offspring even when the parents are trained on only a small random subset of the training dataset in each epoch, thus providing direct confirmation that learned features and behaviour can be successfully transferred from parent networks to offspring in the next generation.