A Draft Memory Model on Spiking Neural Assemblies

TL;DR

This paper introduces a draft memory model for spiking neural networks that learns instantly without weight updates or external algorithms, using spike trapping in neural loops, demonstrated through prime number classification.

Contribution

It presents a novel spike-based memory model that learns immediately and functions as short-term memory without synaptic weight changes or external learning algorithms.

Findings

Successfully classified prime numbers using the model

Demonstrated immediate learning capability

Proposed functional blocks for spike routing and selection

Abstract

A draft memory model (DM) for neural networks with spike propagation delay (SNNwD) is described. Novelty in this approach are that the DM learns immediately, with stimuli presented once, without synaptic weight changes, and without external learning algorithm. Basal on this model is to trap spikes within neural loops. In order to construct the DM we developed two functional blocks, also described herein. The decoder block receives input from a single spikes source and connect it to one among many outputs. The selector block operates in the opposite direction, receiving many spikes sources and connecting one of them to a single output. We realized conceptual proofs by testing the DM in the prime numbers classifying task. This activation-based memory can be used as immediate and short-term memory.