Presentation
ACE-NAS: A Zero-Cost NAS Framework for Co-Design of Architecture and Encoding in Spiking Neural Networks
DescriptionSpiking Neural Networks (SNNs) promise exceptional energy efficiency for neuromorphic computing through event-driven processing. However, unlocking their full potential requires navigating a
complex, strongly coupled design space of network topology and
temporal neural encoding. Existing SNN Neural Architecture Search
(NAS) frameworks typically decouple these dimensions, focusing
exclusively on topology search while relying on manual, fixed encoding schemes. This limitation leaves a vast portion of the design
space unexplored, resulting in sub-optimal energy-accuracy trade-offs. To bridge this gap, we present ACE-NAS, the first zero-cost
NAS framework that automates the co-design of SNN architecture
and encoding mechanisms. Addressing the challenge of "encoding-blind" proxies, we introduce Jacob_cov, a novel Jacobian-based
spectral metric that efficiently quantifies the temporal discriminability of different encoding schemes without training. ACE-NAS
integrates Jacob_cov with structural proxies (ZiCo) into a hardware-aware, multi-objective evolutionary search strategy. On CIFAR-10,
ACE-NAS achieves 92.95% accuracy, effectively identifying Pareto-optimal designs that balance high performance with minimal spike
activity. By automating the joint optimization of structure and
dynamics, ACE-NAS delivers an orders-of-magnitude reduction
compared to standard training-based NAS and a 7× speedup over
state-of-the-art efficient SNN-NAS methods (e.g., AutoSNN).
complex, strongly coupled design space of network topology and
temporal neural encoding. Existing SNN Neural Architecture Search
(NAS) frameworks typically decouple these dimensions, focusing
exclusively on topology search while relying on manual, fixed encoding schemes. This limitation leaves a vast portion of the design
space unexplored, resulting in sub-optimal energy-accuracy trade-offs. To bridge this gap, we present ACE-NAS, the first zero-cost
NAS framework that automates the co-design of SNN architecture
and encoding mechanisms. Addressing the challenge of "encoding-blind" proxies, we introduce Jacob_cov, a novel Jacobian-based
spectral metric that efficiently quantifies the temporal discriminability of different encoding schemes without training. ACE-NAS
integrates Jacob_cov with structural proxies (ZiCo) into a hardware-aware, multi-objective evolutionary search strategy. On CIFAR-10,
ACE-NAS achieves 92.95% accuracy, effectively identifying Pareto-optimal designs that balance high performance with minimal spike
activity. By automating the joint optimization of structure and
dynamics, ACE-NAS delivers an orders-of-magnitude reduction
compared to standard training-based NAS and a 7× speedup over
state-of-the-art efficient SNN-NAS methods (e.g., AutoSNN).
Event Type
Research Manuscript
TimeTuesday, July 284:54pm - 5:06pm PDT
LocationMtg Room 101A