TSkips: Efficiency Through Explicit Temporal Delay Connections in Spiking Neural Networks
Spiking Neural Networks (SNNs) with their bio-inspired Leaky Integrate-and-Fire (LIF) neurons inherently capture temporal information. This makes them well-suited for sequential tasks like processing event-based data from Dynamic Vision Sensors (DVS) and event-based speech tasks. Harnessing the temporal capabilities of SNNs requires mitigating vanishing spikes during training, capturing spatio-temporal patterns and enhancing precise spike timing. To address these challenges, we propose TSkips, augmenting SNN architectures with forward and backward skip connections that incorporate explicit temporal delays. These connections capture long-term spatio-temporal dependencies and facilitate better spike flow over long sequences. The introduction of TSkips creates a vast search space of possible configurations, encompassing skip positions and time delay values. To efficiently navigate this search space, this work leverages training-free Neural Architecture Search (NAS) to identify optimal network structures and corresponding delays. We demonstrate the effectiveness of our approach on four event-based datasets: DSEC-flow for optical flow estimation, DVS128 Gesture for hand gesture recognition and Spiking Heidelberg Digits (SHD) and Spiking Speech Commands (SSC) for speech recognition. Our method achieves significant improvements across these datasets: up to 18% reduction in Average Endpoint Error (AEE) on DSEC-flow, 8% increase in classification accuracy on DVS128 Gesture, and up to 8% and 16% higher classification accuracy on SHD and SSC, respectively.
Code (0)
등록된 구현이 없습니다.
Tasks
Gesture RecognitionHand Gesture RecognitionHand-Gesture RecognitionNavigateNeural Architecture SearchOptical Flow Estimationspeech-recognitionSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Unveiling Delay Effects in Traffic Forecasting: A Perspective from Spatial-Temporal Delay Differential Equations
Traffic flow forecasting is a fundamental research issue for transportation planning and management, which serves as a canonical and typical example of spatial-temporal predictions. In recent years, Graph Neural Networks…
Computational EfficiencyDelayed Memory Unit: Modelling Temporal Dependency Through Delay Gate
Recurrent Neural Networks (RNNs) are widely recognized for their proficiency in modeling temporal dependencies, making them highly prevalent in sequential data processing applications. Nevertheless, vanilla RNNs are conf…
Computational EfficiencyGesture Recognitionimage-classificationImage Classification+3Delay-Empowered Causal Hierarchical Reinforcement Learning
Many real-world tasks involve delayed effects, where the outcomes of actions emerge after varying time lags. Existing delay-aware reinforcement learning methods often rely on state augmentation, prior knowledge of delay …
Hierarchical Reinforcement LearningSpatiotemporal Propagation Learning for Network-Wide Flight Delay Prediction
Demystifying the delay propagation mechanisms among multiple airports is fundamental to precise and interpretable delay prediction, which is crucial during decision-making for all aviation industry stakeholders. The prin…
Decision MakingPredictionTime Series AnalysisPDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction
As a core technology of Intelligent Transportation System, traffic flow prediction has a wide range of applications. The fundamental challenge in traffic flow prediction is to effectively model the complex spatial-tempor…
Computational EfficiencyGraph Neural NetworkPredictionTime Series Analysis+2