Modular Grammatical Evolution for the Generation of Artificial Neural Networks

TL;DR

Modular Grammatical Evolution (MGE) is introduced as a novel approach to generate smaller, more structured neural networks efficiently, achieving superior accuracy and scalability compared to existing methods.

Contribution

MGE extends grammatical evolution with a modular, gene-based representation that improves scalability and locality, enabling the effective evolution of multi-layer neural networks.

Findings

MGE produces simpler classifiers with higher accuracy.

Modularity accelerates neural network discovery.

MGE outperforms existing GE methods in scalability and locality.

Abstract

This paper presents a novel method, called Modular Grammatical Evolution (MGE), towards validating the hypothesis that restricting the solution space of NeuroEvolution to modular and simple neural networks enables the efficient generation of smaller and more structured neural networks while providing acceptable (and in some cases superior) accuracy on large data sets. MGE also enhances the state-of-the-art Grammatical Evolution (GE) methods in two directions. First, MGE's representation is modular in that each individual has a set of genes, and each gene is mapped to a neuron by grammatical rules. Second, the proposed representation mitigates two important drawbacks of GE, namely the low scalability and weak locality of representation, towards generating modular and multi-layer networks with a high number of neurons. We define and evaluate five different forms of structures with and without modularity using MGE and find single-layer modules with no coupling more productive. Our experiments demonstrate that modularity helps in finding better neural networks faster. We have validated the proposed method using ten well-known classification benchmarks with different sizes, feature counts, and output class count. Our experimental results indicate that MGE provides superior accuracy with respect to existing NeuroEvolution methods and returns classifiers that are significantly simpler than other machine learning generated classifiers. Finally, we empirically demonstrate that MGE outperforms other GE methods in terms of locality and scalability properties.