TM-SNN: Threshold Modulated Spiking Neural Network for Multi-task Learning

This paper introduces a spiking neural network able to learn multiple tasks using their unique characteristic, namely, that their behavior can be changed based on the modulation of the firing threshold of spiking neurons. We designed and tested a threshold-modulated spiking neural network (TM-SNN) to solve multiple classification tasks using the approach of learning only one task at a time. The task to be performed is determined by a firing threshold: with one threshold the network learns one task, with the second threshold another task, etc. TM-SNN was implemented on Intel's Loihi2 neuromorphic computer and tested on neuromorphic NMNIST data. The results show that TM-SNN can actually learn different tasks through modifying its dynamics via modulation of the neurons' firing threshold. It is the first application of spiking neural networks to multi-task classification problems.