FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networks

Abstract

Spiking Neural Networks (SNNs) are gaining interest due to their event-driven processing which potentially consumes low power/energy computations in hardware platforms, while offering unsupervised learning capability due to the spike-timing-dependent plasticity (STDP) rule. However, state-of-the-art SNNs require a large memory footprint to achieve high accuracy, thereby making them difficult to be deployed on embedded systems, for instance on battery-powered mobile devices and IoT Edge nodes. Towards this, we propose FSpiNN, an optimization framework for obtaining memory- and energy-efficient SNNs for training and inference processing, with unsupervised learning capability while maintaining accuracy. It is achieved by (1) reducing the computational requirements of neuronal and STDP operations, (2) improving the accuracy of STDP-based learning, (3) compressing the SNN through a fixed-point quantization, and (4) incorporating the memory and energy requirements in the optimization process. FSpiNN reduces the computational requirements by reducing the number of neuronal operations, the STDP-based synaptic weight updates, and the STDP complexity. To improve the accuracy of learning, FSpiNN employs timestep-based synaptic weight updates, and adaptively determines the STDP potentiation factor and the effective inhibition strength. The experimental results show that, as compared to the state-of-the-art work, FSpiNN achieves 7.5x memory saving, and improves the energy-efficiency by 3.5x on average for training and by 1.8x on average for inference, across MNIST and Fashion MNIST datasets, with no accuracy loss for a network with 4900 excitatory neurons, thereby enabling energy-efficient SNNs for edge devices/embedded systems.

To appear at the IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (IEEE-TCAD), as part of the ESWEEK-TCAD Special Issue, September 2020

References in corpus (4)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron
• Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead
• DRMap: A Generic DRAM Data Mapping Policy for Energy-Efficient Processing of Convolutional Neural Networks

Cited by in corpus (28)

• Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Ahead
• Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models
• Q-SpiNN: A Framework for Quantizing Spiking Neural Networks
• Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework
• Spiker: an FPGA-optimized Hardware acceleration for Spiking Neural Networks
• ReSpawn: Energy-Efficient Fault-Tolerance for Spiking Neural Networks considering Unreliable Memories
• Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameters
• SoftSNN: Low-Cost Fault Tolerance for Spiking Neural Network Accelerators under Soft Errors
• SparkXD: A Framework for Resilient and Energy-Efficient Spiking Neural Network Inference using Approximate DRAM
• EnforceSNN: Enabling Resilient and Energy-Efficient Spiking Neural Network Inference considering Approximate DRAMs for Embedded Systems
• Exposing Reliability Degradation and Mitigation in Approximate DNNs under Permanent Faults
• Embodied Neuromorphic Artificial Intelligence for Robotics: Perspectives, Challenges, and Research Development Stack
• SNN4Agents: A Framework for Developing Energy-Efficient Embodied Spiking Neural Networks for Autonomous Agents
• lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agents
• TopSpark: A Timestep Optimization Methodology for Energy-Efficient Spiking Neural Networks on Autonomous Mobile Agents
• RescueSNN: Enabling Reliable Executions on Spiking Neural Network Accelerators under Permanent Faults
• Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications
• SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network-based Embedded AI Systems
• SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environments
• Mantis: Enabling Energy-Efficient Autonomous Mobile Agents with Spiking Neural Networks
• SpiKernel: A Kernel Size Exploration Methodology for Improving Accuracy of the Embedded Spiking Neural Network Systems
• Enabling Efficient Processing of Spiking Neural Networks with On-Chip Learning on Commodity Neuromorphic Processors for Edge AI Systems
• A Methodology to Study the Impact of Spiking Neural Network Parameters considering Event-Based Automotive Data
• QSViT: A Methodology for Quantizing Spiking Vision Transformers
• 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
• Effects of Introducing Synaptic Scaling on Spiking Neural Network Learning