Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN
This work addresses the computational complexity of RSNNs for researchers in neuromorphic computing, offering a novel pruning approach that is incremental but provides specific gains in efficiency and performance.
The paper tackles the problem of designing sparse recurrent spiking neural networks (RSNNs) by introducing a task-agnostic pruning method called Lyapunov Noise Pruning (LNP), which leverages heterogeneity in neuronal timescales to create sparse models that improve computational efficiency and prediction performance compared to traditional activity-based pruning.
Recurrent Spiking Neural Networks (RSNNs) have emerged as a computationally efficient and brain-inspired learning model. The design of sparse RSNNs with fewer neurons and synapses helps reduce the computational complexity of RSNNs. Traditionally, sparse SNNs are obtained by first training a dense and complex SNN for a target task, and, then, pruning neurons with low activity (activity-based pruning) while maintaining task performance. In contrast, this paper presents a task-agnostic methodology for designing sparse RSNNs by pruning a large randomly initialized model. We introduce a novel Lyapunov Noise Pruning (LNP) algorithm that uses graph sparsification methods and utilizes Lyapunov exponents to design a stable sparse RSNN from a randomly initialized RSNN. We show that the LNP can leverage diversity in neuronal timescales to design a sparse Heterogeneous RSNN (HRSNN). Further, we show that the same sparse HRSNN model can be trained for different tasks, such as image classification and temporal prediction. We experimentally show that, in spite of being task-agnostic, LNP increases computational efficiency (fewer neurons and synapses) and prediction performance of RSNNs compared to traditional activity-based pruning of trained dense models.