Continuous learning of spiking networks trained with local rules
This addresses the problem of sequential learning without forgetting for neuromorphic computing, but it is incremental as it adapts existing methods to SNNs.
The paper tackled catastrophic forgetting in spiking neural networks (SNNs) by testing biologically inspired methods, including a novel approach based on stochastic Langevin dynamics, and found that SNNs show potential resilience with these adaptations.
Artificial neural networks (ANNs) experience catastrophic forgetting (CF) during sequential learning. In contrast, the brain can learn continuously without any signs of catastrophic forgetting. Spiking neural networks (SNNs) are the next generation of ANNs with many features borrowed from biological neural networks. Thus, SNNs potentially promise better resilience to CF. In this paper, we study the susceptibility of SNNs to CF and test several biologically inspired methods for mitigating catastrophic forgetting. SNNs are trained with biologically plausible local training rules based on spike-timing-dependent plasticity (STDP). Local training prohibits the direct use of CF prevention methods based on gradients of a global loss function. We developed and tested the method to determine the importance of synapses (weights) based on stochastic Langevin dynamics without the need for the gradients. Several other methods of catastrophic forgetting prevention adapted from analog neural networks were tested as well. The experiments were performed on freely available datasets in the SpykeTorch environment.