Delay Neural Networks (DeNN) for exploiting temporal information in event-based datasets

TL;DR

Delay Neural Networks (DeNN) leverage precise spike timing and synaptic delays to explicitly utilize continuous temporal information in event-based datasets, achieving efficient and effective processing with fewer parameters.

Contribution

This paper introduces Delay Neural Networks (DeNN), a novel neural network class that explicitly models temporal delays and spike times, enhancing temporal data processing in neural networks.

Findings

DeNN perform well on event-based datasets with temporal information.

DeNN use fewer parameters and less energy compared to traditional models.

DeNN outperform some existing models in temporal data tasks.

Abstract

In Deep Neural Networks (DNN) and Spiking Neural Networks (SNN), the information of a neuron is computed based on the sum of the amplitudes (weights) of the electrical potentials received in input from other neurons. We propose here a new class of neural networks, namely Delay Neural Networks (DeNN), where the information of a neuron is computed based on the sum of its input synaptic delays and on the spike times of the electrical potentials received from other neurons. This way, DeNN are designed to explicitly use exact continuous temporal information of spikes in both forward and backward passes, without approximation. (Deep) DeNN are applied here to images and event-based (audio and visual) data sets. Good performances are obtained, especially for datasets where temporal information is important, with much less parameters and less energy than other models.