TopSpark: A Timestep Optimization Methodology for Energy-Efficient Spiking Neural Networks on Autonomous Mobile Agents

Abstract

Autonomous mobile agents require low-power/energy-efficient machine learning (ML) algorithms to complete their ML-based tasks while adapting to diverse environments, as mobile agents are usually powered by batteries. These requirements can be fulfilled by Spiking Neural Networks (SNNs) as they offer low power/energy processing due to their sparse computations and efficient online learning with bio-inspired learning mechanisms for adapting to different environments. Recent works studied that the energy consumption of SNNs can be optimized by reducing the computation time of each neuron for processing a sequence of spikes (timestep). However, state-of-the-art techniques rely on intensive design searches to determine fixed timestep settings for only inference, thereby hindering the SNNs from achieving further energy efficiency gains in both training and inference. These techniques also restrict the SNNs from performing efficient online learning at run time. Toward this, we propose TopSpark, a novel methodology that leverages adaptive timestep reduction to enable energy-efficient SNN processing in both training and inference, while keeping its accuracy close to the accuracy of SNNs without timestep reduction. The ideas of TopSpark include: analyzing the impact of different timesteps on the accuracy; identifying neuron parameters that have a significant impact on accuracy in different timesteps; employing parameter enhancements that make SNNs effectively perform learning and inference using less spiking activity; and developing a strategy to trade-off accuracy, latency, and energy to meet the design requirements. The results show that, TopSpark saves the SNN latency by 3.9x as well as energy consumption by 3.5x (training) and 3.3x (inference) on average, across different network sizes, learning rules, and workloads, while maintaining the accuracy within 2% of SNNs without timestep reduction.

arXiv commentTo appear at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 2023, Detroit, MI, USA

References in corpus (8)

• Deep Learning in Spiking Neural Networks
• BindsNET: A machine learning-oriented spiking neural networks library in Python
• FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networks
• ASP: Learning to Forget with Adaptive Synaptic Plasticity in Spiking Neural Networks
• ReSpawn: Energy-Efficient Fault-Tolerance for Spiking Neural Networks considering Unreliable Memories
• Controlled Forgetting: Targeted Stimulation and Dopaminergic Plasticity Modulation for Unsupervised Lifelong Learning in Spiking Neural Networks
• EnforceSNN: Enabling Resilient and Energy-Efficient Spiking Neural Network Inference considering Approximate DRAMs for Embedded Systems
• lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agents

Cited by in corpus (8)

• Embodied Neuromorphic Artificial Intelligence for Robotics: Perspectives, Challenges, and Research Development Stack
• RescueSNN: Enabling Reliable Executions on Spiking Neural Network Accelerators under Permanent Faults
• SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network-based Embedded AI Systems
• QSViT: A Methodology for Quantizing Spiking Vision Transformers
• A Methodology to Study the Impact of Spiking Neural Network Parameters considering Event-Based Automotive Data
• QSLM: A Performance- and Memory-aware Quantization Framework with Tiered Search Strategy for Spike-driven Language Models
• Replay4NCL: An Efficient Memory Replay-based Methodology for Neuromorphic Continual Learning in Embedded AI Systems
• SpikeVox: Towards Energy-Efficient Speech Therapy Framework with Spike-driven Generative Language Models