A Review of Modularization Techniques in Artificial Neural Networks
This is an incremental review that addresses the need for a more structured understanding of modularization techniques in neural networks for researchers and practitioners in machine learning.
The paper tackles the lack of systematic analysis in modular neural networks (MNNs) by establishing a solid taxonomy to capture the essential properties and relationships of different modularization techniques, aiming to provide a universal framework for theorists and highlight good practices for practitioners.
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.