AutoSNN: Towards Energy-Efficient Spiking Neural Networks
This work addresses the need for more efficient and accurate SNNs for neuromorphic computing applications, representing an incremental improvement by focusing on architecture rather than training methods.
The paper tackles the problem of improving accuracy and energy efficiency in spiking neural networks (SNNs) by addressing architectural design choices, which were previously overlooked, and proposes AutoSNN, a spike-aware neural architecture search framework that successfully searches for SNN architectures outperforming hand-crafted ones in both accuracy and energy efficiency.
Spiking neural networks (SNNs) that mimic information transmission in the brain can energy-efficiently process spatio-temporal information through discrete and sparse spikes, thereby receiving considerable attention. To improve accuracy and energy efficiency of SNNs, most previous studies have focused solely on training methods, and the effect of architecture has rarely been studied. We investigate the design choices used in the previous studies in terms of the accuracy and number of spikes and figure out that they are not best-suited for SNNs. To further improve the accuracy and reduce the spikes generated by SNNs, we propose a spike-aware neural architecture search framework called AutoSNN. We define a search space consisting of architectures without undesirable design choices. To enable the spike-aware architecture search, we introduce a fitness that considers both the accuracy and number of spikes. AutoSNN successfully searches for SNN architectures that outperform hand-crafted SNNs in accuracy and energy efficiency. We thoroughly demonstrate the effectiveness of AutoSNN on various datasets including neuromorphic datasets.