# A Review of Modularization Techniques in Artificial Neural Networks

## TL;DR

This paper systematically reviews modularization techniques in artificial neural networks, establishing a taxonomy to better understand their properties, strengths, and weaknesses for scalable and complex machine learning applications.

## Contribution

It provides the first comprehensive taxonomy of MNNs, analyzing various modularization techniques and their relationships, which aids both theorists and practitioners.

## Key findings

- Developed a universal taxonomy for MNNs
- Analyzed strengths and weaknesses of different modularization approaches
- Highlighted good practices for neural network modularization

## Abstract

Artificial neural networks (ANNs) have achieved significant success in tackling classical and modern machine learning problems. As learning problems grow in scale and complexity, and expand into multi-disciplinary territory, a more modular approach for scaling ANNs will be needed. Modular neural networks (MNNs) are neural networks that embody the concepts and principles of modularity. MNNs adopt a large number of different techniques for achieving modularization. Previous surveys of modularization techniques are relatively scarce in their systematic analysis of MNNs, focusing mostly on empirical comparisons and lacking an extensive taxonomical framework. In this review, we aim to establish a solid taxonomy that captures the essential properties and relationships of the different variants of MNNs. Based on an investigation of the different levels at which modularization techniques act, we attempt to provide a universal and systematic framework for theorists studying MNNs, also trying along the way to emphasise the strengths and weaknesses of different modularization approaches in order to highlight good practices for neural network practitioners.