LightSNN: Lightweight Architecture Search for Sparse and Accurate Spiking Neural Networks

LightSNN: Lightweight Architecture Search for Sparse and Accurate Spiking Neural Networks Y esmine Abdennadher, Giovanni Perin,, Riccardo Mazzieri, Jacopo Pegoraro, and Michele Rossi Department of Information Engineering (DEI), University of Padova, Padova, Italy Department of Information Engineering (DII), University of Brescia, Brescia, Italy Abstract --Spiking Neural Networks (SNNs) are highly regarded for their energy efficiency, inherent activation sparsity, and suitability for real-time processing in edge devices. However, most current SNN methods adopt architectures resembling traditional artificial neural networks (ANNs), leading to suboptimal performance when applied to SNNs. While SNNs excel in energy efficiency, they have been associated with lower accuracy levels than traditional ANNs when utilizing conventional architectures. In response, in this work we present LightSNN, a rapid and efficient Neural Network Architecture Search (NAS) technique specifically tailored for SNNs that autonomously leverages the most suitable architecture, striking a good balance between accuracy and efficiency by enforcing sparsity. Based on the spiking NAS network (SNASNet) framework, a cell-based search space including backward connections is utilized to build our training-free pruning-based NAS mechanism. Thorough experiments are conducted on both static (CIF AR10 and CIF AR100) and neuromorphic datasets (DVS128-Gesture).