Training Spiking Neural Networks for Cognitive Tasks: A Versatile Framework Compatible to Various Temporal Codes

TL;DR

This paper presents a versatile framework for training spiking neural networks on various cognitive tasks using a modified SpikeProp algorithm, incorporating biological features and demonstrating emergent neural properties.

Contribution

It introduces a modified SpikeProp learning algorithm and a unified framework capable of implementing multiple temporal codes for diverse cognitive tasks.

Findings

Improved learning stability across activity states

Inclusion of biological features like lateral connections and sparse activity

Emergence of neural features such as selectivity and excitatory-inhibitory balance

Abstract

Conventional modeling approaches have found limitations in matching the increasingly detailed neural network structures and dynamics recorded in experiments to the diverse brain functionalities. On another approach, studies have demonstrated to train spiking neural networks for simple functions using supervised learning. Here, we introduce a modified SpikeProp learning algorithm, which achieved better learning stability in different activity states. In addition, we show biological realistic features such as lateral connections and sparse activities can be included in the network. We demonstrate the versatility of this framework by implementing three well-known temporal codes for different types of cognitive tasks, which are MNIST digits recognition, spatial coordinate transformation, and motor sequence generation. Moreover, we find several characteristic features have evolved alongside the task training, such as selective activity, excitatory-inhibitory balance, and weak pair-wise correlation. The coincidence between the self-evolved and experimentally observed features indicates their importance on the brain functionality. Our results suggest a unified setting in which diverse cognitive computations and mechanisms can be studied.