MT-SNN: Spiking Neural Network that Enables Single-Tasking of Multiple Tasks

TL;DR

This paper introduces MT-SNN, a multi-task spiking neural network that can learn and switch between multiple classification tasks by adjusting neuron firing thresholds, demonstrating effective multitask learning on neuromorphic hardware.

Contribution

The paper presents a novel multi-task SNN architecture that enables single-tasking of multiple tasks through threshold modulation, implemented on the Loihi2 chip.

Findings

MT-SNN effectively learns multiple tasks by adjusting neuron firing thresholds.

The network successfully performs dynamic multitask classification on NMNIST data.

Threshold modulation allows flexible switching between tasks.

Abstract

In this paper we explore capabilities of spiking neural networks in solving multi-task classification problems using the approach of single-tasking of multiple tasks. We designed and implemented a multi-task spiking neural network (MT-SNN) that can learn two or more classification tasks while performing one task at a time. The task to perform is selected by modulating the firing threshold of leaky integrate and fire neurons used in this work. The network is implemented using Intel's Lava platform for the Loihi2 neuromorphic chip. Tests are performed on dynamic multitask classification for NMNIST data. The results show that MT-SNN effectively learns multiple tasks by modifying its dynamics, namely, the spiking neurons' firing threshold.