SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron

Abstract

Application of deep convolutional spiking neural networks (SNNs) to artificial intelligence (AI) tasks has recently gained a lot of interest since SNNs are hardware-friendly and energy-efficient. Unlike the non-spiking counterparts, most of the existing SNN simulation frameworks are not practically efficient enough for large-scale AI tasks. In this paper, we introduce SpykeTorch, an open-source high-speed simulation framework based on PyTorch. This framework simulates convolutional SNNs with at most one spike per neuron and the rank-order encoding scheme. In terms of learning rules, both spike-timing-dependent plasticity (STDP) and reward-modulated STDP (R-STDP) are implemented, but other rules could be implemented easily. Apart from the aforementioned properties, SpykeTorch is highly generic and capable of reproducing the results of various studies. Computations in the proposed framework are tensor-based and totally done by PyTorch functions, which in turn brings the ability of just-in-time optimization for running on CPUs, GPUs, or Multi-GPU platforms.

References in corpus (12)

• Deep Learning in Spiking Neural Networks
• Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks
• STDP-based spiking deep convolutional neural networks for object recognition
• SuperSpike: Supervised learning in multi-layer spiking neural networks
• SLAYER: Spike Layer Error Reassignment in Time
• BindsNET: A machine learning-oriented spiking neural networks library in Python
• First-spike based visual categorization using reward-modulated STDP
• Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks
• Surrogate Gradient Learning in Spiking Neural Networks
• Bio-inspired Unsupervised Learning of Visual Features Leads to Robust Invariant Object Recognition
• Bio-Inspired Spiking Convolutional Neural Network using Layer-wise Sparse Coding and STDP Learning
• Deep Convolutional Spiking Neural Networks for Image Classification

Cited by in corpus (22)

• S4NN: temporal backpropagation for spiking neural networks with one spike per neuron
• Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks
• BS4NN: Binarized Spiking Neural Networks with Temporal Coding and Learning
• FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networks
• Q-SpiNN: A Framework for Quantizing Spiking Neural Networks
• Design Space Exploration of Hardware Spiking Neurons for Embedded Artificial Intelligence
• RANC: Reconfigurable Architecture for Neuromorphic Computing
• Simple and complex spiking neurons: perspectives and analysis in a simple STDP scenario
• EnforceSNN: Enabling Resilient and Energy-Efficient Spiking Neural Network Inference considering Approximate DRAMs for Embedded Systems
• Continuous learning of spiking networks trained with local rules
• RescueSNN: Enabling Reliable Executions on Spiking Neural Network Accelerators under Permanent Faults
• Multi-GPU SNN Simulation with Static Load Balancing
• Faster and Simpler SNN Simulation with Work Queues
• Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications
• Energy efficiency analysis of Spiking Neural Networks for space applications
• Learning through structure: towards deep neuromorphic knowledge graph embeddings
• Exploring the Back Alleys: Analysing The Robustness of Alternative Neural Network Architectures against Adversarial Attacks
• A Deep Unsupervised Feature Learning Spiking Neural Network with Binarized Classification Layers for EMNIST Classification using SpykeFlow
• Even Faster SNN Simulation with Lazy+Event-driven Plasticity and Shared Atomics
• QSLM: A Performance- and Memory-aware Quantization Framework with Tiered Search Strategy for Spike-driven Language Models
• SpikeVox: Towards Energy-Efficient Speech Therapy Framework with Spike-driven Generative Language Models
• 2D versus 3D Convolutional Spiking Neural Networks Trained with Unsupervised STDP for Human Action Recognition