SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks With at Most One Spike per Neuron

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.

[1]  Pierre Tirilly,et al.  Multi-layered Spiking Neural Network with Target Timestamp Threshold Adaptation and STDP , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[2]  Denis Fize,et al.  Speed of processing in the human visual system , 1996, Nature.

[3]  Marc-Oliver Gewaltig,et al.  NEST (NEural Simulation Tool) , 2007, Scholarpedia.

[4]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[5]  Abbas Nowzari-Dalini,et al.  Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks , 2019, Pattern Recognit..

[6]  W. Gerstner,et al.  Neuromodulated Spike-Timing-Dependent Plasticity, and Theory of Three-Factor Learning Rules , 2016, Front. Neural Circuits.

[7]  Tao Liu,et al.  MT-spike: A multilayer time-based spiking neuromorphic architecture with temporal error backpropagation , 2017, 2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).

[8]  Matthew Cook,et al.  Unsupervised learning of digit recognition using spike-timing-dependent plasticity , 2015, Front. Comput. Neurosci..

[9]  Darpan T. Sanghavi,et al.  BindsNET: A Machine Learning-Oriented Spiking Neural Networks Library in Python , 2018, Front. Neuroinform..

[10]  Trevor Bekolay,et al.  Nengo: a Python tool for building large-scale functional brain models , 2014, Front. Neuroinform..

[11]  Shaista Hussain,et al.  Improved margin multi-class classification using dendritic neurons with morphological learning , 2014, 2014 IEEE International Symposium on Circuits and Systems (ISCAS).

[12]  Michael L. Hines,et al.  The NEURON Book , 2006 .

[13]  S. Thorpe,et al.  STDP-based spiking deep convolutional neural networks for object recognition , 2018 .

[14]  Douglas Galasko,et al.  NPTX2 and cognitive dysfunction in Alzheimer’s Disease , 2017, eLife.

[15]  Romain Brette,et al.  Equation-oriented specification of neural models for simulations , 2013, Front. Neuroinform..

[16]  Emre Neftci,et al.  Surrogate Gradient Learning in Spiking Neural Networks: Bringing the Power of Gradient-based optimization to spiking neural networks , 2019, IEEE Signal Processing Magazine.

[17]  Julien Vitay,et al.  ANNarchy: a code generation approach to neural simulations on parallel hardware , 2015, Front. Neuroinform..

[18]  Matthew Cook,et al.  Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[19]  Garrick Orchard,et al.  SLAYER: Spike Layer Error Reassignment in Time , 2018, NeurIPS.

[20]  Timothée Masquelier,et al.  Bio-inspired unsupervised learning of visual features leads to robust invariant object recognition , 2015, Neurocomputing.

[21]  Hong Wang,et al.  Loihi: A Neuromorphic Manycore Processor with On-Chip Learning , 2018, IEEE Micro.

[22]  Vishal Saxena,et al.  Deep Convolutional Spiking Neural Networks for Image Classification , 2019, ArXiv.

[23]  Timothée Masquelier,et al.  First-Spike-Based Visual Categorization Using Reward-Modulated STDP , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[24]  Tobi Delbruck,et al.  Real-time classification and sensor fusion with a spiking deep belief network , 2013, Front. Neurosci..

[25]  Anthony S. Maida,et al.  Bio-Inspired Spiking Convolutional Neural Network using Layer-wise Sparse Coding and STDP Learning , 2016, ArXiv.

[26]  Wulfram Gerstner,et al.  A neuronal learning rule for sub-millisecond temporal coding , 1996, Nature.

[27]  Hesham Mostafa,et al.  Supervised Learning Based on Temporal Coding in Spiking Neural Networks , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[28]  Michael Pfeiffer,et al.  Deep Learning With Spiking Neurons: Opportunities and Challenges , 2018, Front. Neurosci..

[29]  Franck Mamalet,et al.  Unsupervised Feature Learning With Winner-Takes-All Based STDP , 2018, Front. Comput. Neurosci..

[30]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[31]  Antoine Dupret,et al.  Event-Based, Timescale Invariant Unsupervised Online Deep Learning With STDP , 2018, Front. Comput. Neurosci..

[32]  Surya Ganguli,et al.  SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks , 2017, Neural Computation.

[33]  Bernabé Linares-Barranco,et al.  Hardware implementation of convolutional STDP for on-line visual feature learning , 2017, 2017 IEEE International Symposium on Circuits and Systems (ISCAS).

[34]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[35]  Razvan V. Florian,et al.  Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic Plasticity , 2007, Neural Computation.

[36]  Timothée Masquelier,et al.  Deep Learning in Spiking Neural Networks , 2018, Neural Networks.

[37]  Nikola K. Kasabov,et al.  NeuCube: A spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data , 2014, Neural Networks.

[38]  Robert A. Legenstein,et al.  Long short-term memory and Learning-to-learn in networks of spiking neurons , 2018, NeurIPS.

[39]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[40]  Lei Deng,et al.  Spatio-Temporal Backpropagation for Training High-Performance Spiking Neural Networks , 2017, Front. Neurosci..

[41]  Deepak Khosla,et al.  Spiking Deep Convolutional Neural Networks for Energy-Efficient Object Recognition , 2014, International Journal of Computer Vision.

[42]  G. Bi,et al.  Synaptic Modifications in Cultured Hippocampal Neurons: Dependence on Spike Timing, Synaptic Strength, and Postsynaptic Cell Type , 1998, The Journal of Neuroscience.

[43]  J. Mink,et al.  Ratio of central nervous system to body metabolism in vertebrates: its constancy and functional basis. , 1981, The American journal of physiology.

[44]  Haizhou Li,et al.  Rapid Feedforward Computation by Temporal Encoding and Learning With Spiking Neurons , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[46]  Zenghui Wang,et al.  Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review , 2017, Neural Computation.

[47]  Ting Liu,et al.  Recent advances in convolutional neural networks , 2015, Pattern Recognit..

[48]  W. Schultz,et al.  Sequential neuromodulation of Hebbian plasticity offers mechanism for effective reward-based navigation , 2017, eLife.

[49]  Timothée Masquelier,et al.  Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity , 2007, PLoS Comput. Biol..

[50]  Simon J. Thorpe,et al.  Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks , 2018, Pattern Recognit..

[51]  Manish Kumar.  Large-scale neuromorphic computing systems , 2016 .