Continuous-Time Neural Networks Can Stably Memorize Random Spike Trains

TL;DR

This paper demonstrates that continuous-time recurrent neural networks can reliably memorize and recall random spike train patterns with stable timing, even under noisy conditions, by using offline computed synaptic weights.

Contribution

It shows for the first time that continuous-time neural networks can stably memorize and recall random spike trains with high probability, including under noisy conditions.

Findings

Networks can memorize spike trains with stable timing.

Recall remains accurate under noise.

Synaptic weights are computed offline for stability.

Abstract

The paper explores the capability of continuous-time recurrent neural networks to store and recall precisely timed scores of spike trains. We show (by numerical experiments) that this is indeed possible: within some range of parameters, any random score of spike trains (for all neurons in the network) can be robustly memorized and autonomously reproduced with stable accurate relative timing of all spikes, with probability close to one. We also demonstrate associative recall under noisy conditions. In these experiments, the required synaptic weights are computed offline, to satisfy a template that encourages temporal stability.