Limited Evaluation Cooperative Co-evolutionary Differential Evolution for Large-scale Neuroevolution

TL;DR

This paper introduces LECCDE, a novel neuroevolution method that efficiently optimizes large neural networks by combining cooperative co-evolution and limited evaluation, reducing computation time while improving test accuracy.

Contribution

The paper presents LECCDE, a new approach that enhances large-scale neural network optimization through cooperative co-evolution and fitness inheritance, addressing scalability and efficiency issues.

Findings

LECCDE outperforms standard Differential Evolution in test error.

The limited evaluation scheme reduces computational time significantly.

Cooperative co-evolution improves optimization for high-dimensional ANNs.

Abstract

Many real-world control and classification tasks involve a large number of features. When artificial neural networks (ANNs) are used for modeling these tasks, the network architectures tend to be large. Neuroevolution is an effective approach for optimizing ANNs; however, there are two bottlenecks that make their application challenging in case of high-dimensional networks using direct encoding. First, classic evolutionary algorithms tend not to scale well for searching large parameter spaces; second, the network evaluation over a large number of training instances is in general time-consuming. In this work, we propose an approach called the Limited Evaluation Cooperative Co-evolutionary Differential Evolution algorithm (LECCDE) to optimize high-dimensional ANNs. The proposed method aims to optimize the pre-synaptic weights of each post-synaptic neuron in different subpopulations using a Cooperative Co-evolutionary Differential Evolution algorithm, and employs a limited evaluation scheme where fitness evaluation is performed on a relatively small number of training instances based on fitness inheritance. We test LECCDE on three datasets with various sizes, and our results show that cooperative co-evolution significantly improves the test error comparing to standard Differential Evolution, while the limited evaluation scheme facilitates a significant reduction in computing time.