On the Algorithmic Power of Spiking Neural Networks

TL;DR

This paper rigorously analyzes the computational capabilities of simplified Spiking Neural Networks (SNN), demonstrating their ability to solve quadratic and l1 minimization problems through a dual primal-dual algorithm perspective.

Contribution

It provides the first rigorous asymptotic analysis of SNN's performance in solving optimization problems, confirming empirical observations and introducing a dual view of SNN dynamics.

Findings

SNN can solve quadratic programming problems efficiently.

In cases with multiple optima, SNN converges to solutions with smaller l1 norm.

SNN can solve l1 minimization problems under certain conditions.

Abstract

Spiking Neural Networks (SNN) are mathematical models in neuroscience to describe the dynamics among a set of neurons that interact with each other by firing instantaneous signals, a.k.a., spikes. Interestingly, a recent advance in neuroscience [Barrett-Den\`eve-Machens, NIPS 2013] showed that the neurons' firing rate, i.e., the average number of spikes fired per unit of time, can be characterized by the optimal solution of a quadratic program defined by the parameters of the dynamics. This indicated that SNN potentially has the computational power to solve non-trivial quadratic programs. However, the results were justified empirically without rigorous analysis. We put this into the context of natural algorithms and aim to investigate the algorithmic power of SNN. Especially, we emphasize on giving rigorous asymptotic analysis on the performance of SNN in solving optimization problems. To enforce a theoretical study, we first identify a simplified SNN model that is tractable for analysis. Next, we confirm the empirical observation in the work of Barrett et al. by giving an upper bound on the convergence rate of SNN in solving the quadratic program. Further, we observe that in the case where there are infinitely many optimal solutions, SNN tends to converge to the one with smaller l1 norm. We give an affirmative answer to our finding by showing that SNN can solve the l1 minimization problem under some regular conditions. Our main technical insight is a dual view of the SNN dynamics, under which SNN can be viewed as a new natural primal-dual algorithm for the l1 minimization problem. We believe that the dual view is of independent interest and may potentially find interesting interpretation in neuroscience.