Memory via Temporal Delays in weightless Spiking Neural Network

TL;DR

This paper introduces a weightless spiking neural network model that encodes memory through neuron timing delays instead of connection weights, trained with Hebbian STDP for simple classification tasks.

Contribution

It presents a novel weightless neural network architecture that uses timing delays for memory storage, diverging from traditional weight-based models.

Findings

Successfully performs simple classification tasks

Demonstrates memory encoding via timing delays

Uses Hebbian STDP to modulate delays

Abstract

A common view in the neuroscience community is that memory is encoded in the connection strength between neurons. This perception led artificial neural network models to focus on connection weights as the key variables to modulate learning. In this paper, we present a prototype for weightless spiking neural networks that can perform a simple classification task. The memory in this network is stored in the timing between neurons, rather than the strength of the connection, and is trained using a Hebbian Spike Timing Dependent Plasticity (STDP), which modulates the delays of the connection.