Role of Delay in Brain Dynamics

TL;DR

This paper introduces the RoDiB model, which leverages multiple delays in neural networks to turn the disadvantage of asynchronous brain dynamics into a computational advantage, enabling efficient multi-label classification.

Contribution

The study presents the RoDiB model that uses multiple delays to improve learning capacity and accuracy without changing the network architecture.

Findings

RoDiB achieves comparable accuracy to tunable delay architectures.

Accuracy improves with more output labels than input size.

Simulations on CIFAR datasets demonstrate the model's effectiveness.

Abstract

Significant variations of delays among connecting neurons cause an inevitable disadvantage of asynchronous brain dynamics compared to synchronous deep learning. However, this study demonstrates that this disadvantage can be converted into a computational advantage using a network with a single output and M multiple delays between successive layers, thereby generating a polynomial time-series outputs with M. The proposed role of delay in brain dynamics (RoDiB) model, is capable of learning increasing number of classified labels using a fixed architecture, and overcomes the inflexibility of the brain to update the learning architecture using additional neurons and connections. Moreover, the achievable accuracies of the RoDiB system are comparable with those of its counterpart tunable single delay architectures with M outputs. Further, the accuracies are significantly enhanced when the number of output labels exceeds its fully connected input size. The results are mainly obtained using simulations of VGG-6 on CIFAR datasets and also include multiple label inputs. However, currently only a small fraction of the abundant number of RoDiB outputs is utilized, thereby suggesting its potential for advanced computational power yet to be discovered.