Artificial Neural Microcircuits as Building Blocks: Concept and Challenges
This addresses the problem of designing more robust and reusable neural network components for researchers and practitioners in machine learning, though it appears incremental as it builds on existing bio-inspired concepts.
The paper tackles the structural homogeneity and overfitting issues in Artificial Neural Networks by proposing Artificial Neural Microcircuits as off-the-shelf building blocks for assembling larger networks, particularly Spiking Neural Networks, with initial results from using Novelty Search to create a catalogue of such microcircuits.
Artificial Neural Networks (ANNs) are one of the most widely employed forms of bio-inspired computation. However the current trend is for ANNs to be structurally homogeneous. Furthermore, this structural homogeneity requires the application of complex training and learning tools that produce application specific ANNs, susceptible to pitfalls such as overfitting. In this paper, an new approach is explored, inspired by the role played in biology by Neural Microcircuits, the so called ``fundamental processing elements'' of organic nervous systems. How large neural networks, particularly Spiking Neural Networks (SNNs) can be assembled using Artificial Neural Microcircuits (ANMs), intended as off-the-shelf components, is articulated; the results of initial work to produce a catalogue of such Microcircuits though the use of Novelty Search is shown; followed by efforts to expand upon this initial work, including a discussion of challenges uncovered during these efforts and explorations of methods by which they might be overcome.