Brain-Inspired Learning on Neuromorphic Substrates

Neuromorphic hardware strives to emulate brain-like neural networks and thus holds the promise for scalable, low-power information processing on temporal data streams. Yet, to solve real-world problems, these networks need to be trained. However, training on neuromorphic substrates creates significant challenges due to the offline character and the required non-local computations of gradient-based learning algorithms. This article provides a mathematical framework for the design of practical online learning algorithms for neuromorphic substrates. Specifically, we show a direct connection between Real-Time Recurrent Learning (RTRL), an online algorithm for computing gradients in conventional Recurrent Neural Networks (RNNs), and biologically plausible learning rules for training Spiking Neural Networks (SNNs). Further, we motivate a sparse approximation based on block-diagonal Jacobians, which reduces the algorithm's computational complexity, diminishes the non-local information requirements, and empirically leads to good learning performance, thereby improving its applicability to neuromorphic substrates. In summary, our framework bridges the gap between synaptic plasticity and gradient-based approaches from deep learning and lays the foundations for powerful information processing on future neuromorphic hardware systems.

[1]  Wulfram Gerstner,et al.  Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network , 2017, eLife.

[2]  Melika Payvand,et al.  Error-triggered Three-Factor Learning Dynamics for Crossbar Arrays , 2019, 2020 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS).

[3]  Friedemann Zenke,et al.  The Heidelberg Spiking Data Sets for the Systematic Evaluation of Spiking Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[4]  S. Grossberg,et al.  The Adaptive Brain , 1990 .

[5]  Michael J. Frank,et al.  Making Working Memory Work: A Computational Model of Learning in the Prefrontal Cortex and Basal Ganglia , 2006, Neural Computation.

[6]  Erich Elsen,et al.  A Practical Sparse Approximation for Real Time Recurrent Learning , 2020, ArXiv.

[7]  Jean-Jacques E. Slotine,et al.  Collective Stability of Networks of Winner-Take-All Circuits , 2011, Neural Computation.

[8]  Uwe Naumann,et al.  The Art of Differentiating Computer Programs - An Introduction to Algorithmic Differentiation , 2012, Software, environments, tools.

[9]  Rodolphe Sepulchre,et al.  Neuronal behaviors: A control perspective , 2015, 2015 54th IEEE Conference on Decision and Control (CDC).

[10]  Kaushik Roy,et al.  Enabling Spike-Based Backpropagation for Training Deep Neural Network Architectures , 2019, Frontiers in Neuroscience.

[11]  Jean-Pascal Pfister,et al.  Optimal Spike-Timing-Dependent Plasticity for Precise Action Potential Firing in Supervised Learning , 2005, Neural Computation.

[12]  H. Sompolinsky,et al.  The tempotron: a neuron that learns spike timing–based decisions , 2006, Nature Neuroscience.

[13]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[14]  Mark C. W. van Rossum,et al.  A Novel Spike Distance , 2001, Neural Computation.

[15]  Andrew S. Cassidy,et al.  Convolutional networks for fast, energy-efficient neuromorphic computing , 2016, Proceedings of the National Academy of Sciences.

[16]  Uwe Naumann,et al.  Optimal Jacobian accumulation is NP-complete , 2007, Math. Program..

[17]  L. F. Abbott,et al.  Building functional networks of spiking model neurons , 2016, Nature Neuroscience.

[18]  W. Senn,et al.  Matching Recall and Storage in Sequence Learning with Spiking Neural Networks , 2013, The Journal of Neuroscience.

[19]  Andreas Griewank,et al.  Evaluating derivatives - principles and techniques of algorithmic differentiation, Second Edition , 2000, Frontiers in applied mathematics.

[20]  Yoshua Bengio,et al.  Dendritic cortical microcircuits approximate the backpropagation algorithm , 2018, NeurIPS.

[21]  Wolfgang Maass,et al.  A solution to the learning dilemma for recurrent networks of spiking neurons , 2019, Nature Communications.

[22]  Tobi Delbrück,et al.  Training Deep Spiking Neural Networks Using Backpropagation , 2016, Front. Neurosci..

[23]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[24]  Friedemann Zenke,et al.  The remarkable robustness of surrogate gradient learning for instilling complex function in spiking neural networks , 2020, bioRxiv.

[25]  Federico Corradi,et al.  Effective and Efficient Computation with Multiple-timescale Spiking Recurrent Neural Networks , 2020, ICONS.

[26]  Timothy P Lillicrap,et al.  Towards deep learning with segregated dendrites , 2016, eLife.

[27]  Everton J. Agnes,et al.  Diverse synaptic plasticity mechanisms orchestrated to form and retrieve memories in spiking neural networks , 2015, Nature Communications.

[28]  Siddharth Joshi,et al.  Memory-Efficient Synaptic Connectivity for Spike-Timing- Dependent Plasticity , 2019, Front. Neurosci..

[29]  Rodney J. Douglas,et al.  A pulse-coded communications infrastructure for neuromorphic systems , 1999 .

[30]  Barak A. Pearlmutter,et al.  Automatic differentiation in machine learning: a survey , 2015, J. Mach. Learn. Res..

[31]  Gert Cauwenberghs,et al.  Deep Supervised Learning Using Local Errors , 2017, Front. Neurosci..

[32]  E. Izhikevich Solving the distal reward problem through linkage of STDP and dopamine signaling , 2007, BMC Neuroscience.

[33]  Giacomo Indiveri,et al.  A Systematic Method for Configuring VLSI Networks of Spiking Neurons , 2011, Neural Computation.

[34]  Johannes Schemmel,et al.  An accelerated analog neuromorphic hardware system emulating NMDA- and calcium-based non-linear dendrites , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[35]  Evangelos Eleftheriou,et al.  Online spatio-temporal learning in deep neural networks , 2020, ArXiv.

[36]  Shih-Chii Liu,et al.  Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification , 2017, Front. Neurosci..

[37]  Wulfram Gerstner,et al.  Neuronal Dynamics: From Single Neurons To Networks And Models Of Cognition , 2014 .

[38]  John Salvatier,et al.  Theano: A Python framework for fast computation of mathematical expressions , 2016, ArXiv.

[39]  Hesham Mostafa,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.

[40]  Michael Carbin,et al.  The Lottery Ticket Hypothesis: Training Pruned Neural Networks , 2018, ArXiv.

[41]  Philip H. S. Torr,et al.  SNIP: Single-shot Network Pruning based on Connection Sensitivity , 2018, ICLR.

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

[43]  Wilten Nicola,et al.  Supervised learning in spiking neural networks with FORCE training , 2016, Nature Communications.

[44]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[45]  Carver A. Mead,et al.  Neuromorphic electronic systems , 1990, Proc. IEEE.

[46]  Surya Ganguli,et al.  A deep learning framework for neuroscience , 2019, Nature Neuroscience.

[47]  David A. Patterson,et al.  In-datacenter performance analysis of a tensor processing unit , 2017, 2017 ACM/IEEE 44th Annual International Symposium on Computer Architecture (ISCA).

[48]  Osvaldo Simeone,et al.  An Introduction to Probabilistic Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications , 2019, IEEE Signal Processing Magazine.

[49]  Robert Gütig,et al.  Spiking neurons can discover predictive features by aggregate-label learning , 2016, Science.

[50]  Osvaldo Simeone,et al.  VOWEL: A Local Online Learning Rule for Recurrent Networks of Probabilistic Spiking Winner- Take-All Circuits , 2020, 2020 25th International Conference on Pattern Recognition (ICPR).

[51]  Diederik P. Kingma,et al.  GPU Kernels for Block-Sparse Weights , 2017 .

[52]  Peter Sterling,et al.  Principles of Neural Design , 2015 .

[53]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[54]  John Wawrzynek,et al.  Silicon Auditory Processors as Computer Peripherals , 1992, NIPS.

[55]  Colin J. Akerman,et al.  Random synaptic feedback weights support error backpropagation for deep learning , 2016, Nature Communications.

[56]  Surya Ganguli,et al.  Improved multitask learning through synaptic intelligence , 2017, ArXiv.

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

[58]  Yali Amit,et al.  Deep Learning With Asymmetric Connections and Hebbian Updates , 2018, Front. Comput. Neurosci..

[59]  Pierre Yger,et al.  Slow feature analysis with spiking neurons and its application to audio stimuli , 2016, Journal of Computational Neuroscience.

[60]  Osvaldo Simeone,et al.  An Introduction to Probabilistic Spiking Neural Networks. , 2019 .

[61]  Giacomo Indiveri,et al.  A Scalable Multicore Architecture With Heterogeneous Memory Structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs) , 2017, IEEE Transactions on Biomedical Circuits and Systems.

[62]  Emre O. Neftci,et al.  Data and Power Efficient Intelligence with Neuromorphic Learning Machines , 2018, iScience.

[63]  Johannes Schemmel,et al.  A comprehensive workflow for general-purpose neural modeling with highly configurable neuromorphic hardware systems , 2010, Biological Cybernetics.

[64]  Léon Bottou,et al.  Sn: A simulator for connectionist models , 1988 .

[65]  Sander M. Bohte,et al.  SpikeProp: backpropagation for networks of spiking neurons , 2000, ESANN.

[66]  Erich Elsen,et al.  Rigging the Lottery: Making All Tickets Winners , 2020, ICML.

[67]  Pete Warden,et al.  Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition , 2018, ArXiv.

[68]  Terrence J. Sejnowski,et al.  Simple framework for constructing functional spiking recurrent neural networks , 2019, Proceedings of the National Academy of Sciences.

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

[70]  T. Toyoizumi,et al.  Learning with three factors: modulating Hebbian plasticity with errors , 2017, Current Opinion in Neurobiology.

[71]  Kyunghyun Cho,et al.  A Unified Framework of Online Learning Algorithms for Training Recurrent Neural Networks , 2019, J. Mach. Learn. Res..

[72]  Andrew S. Cassidy,et al.  A million spiking-neuron integrated circuit with a scalable communication network and interface , 2014, Science.

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

[74]  Gert Cauwenberghs,et al.  Neuromorphic Silicon Neuron Circuits , 2011, Front. Neurosci.

[75]  Giacomo Indiveri,et al.  A current-mode conductance-based silicon neuron for address-event neuromorphic systems , 2009, 2009 IEEE International Symposium on Circuits and Systems.

[76]  Michael Carbin,et al.  The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks , 2018, ICLR.

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

[78]  Pierre Baldi,et al.  Learning in the machine: Random backpropagation and the deep learning channel , 2016, Artif. Intell..

[79]  Gert Cauwenberghs,et al.  Hierarchical Address Event Routing for Reconfigurable Large-Scale Neuromorphic Systems , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[80]  Romain Brette,et al.  Neuroinformatics Original Research Article Brian: a Simulator for Spiking Neural Networks in Python , 2022 .

[81]  Classifying Images with Few Spikes per Neuron , 2020, ArXiv.

[82]  Adam Santoro,et al.  Backpropagation and the brain , 2020, Nature Reviews Neuroscience.

[83]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[84]  Wulfram Gerstner,et al.  Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of NeoHebbian Three-Factor Learning Rules , 2018, Front. Neural Circuits.

[85]  Daniel J. Amit,et al.  Modeling brain function: the world of attractor neural networks, 1st Edition , 1989 .

[86]  André Grüning,et al.  Learning Spatiotemporally Encoded Pattern Transformations in Structured Spiking Neural Networks , 2015, Neural Computation.

[87]  Kilian Q. Weinberger,et al.  CondenseNet: An Efficient DenseNet Using Learned Group Convolutions , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[88]  Mike E. Davies,et al.  Benchmarks for progress in neuromorphic computing , 2019, Nature Machine Intelligence.

[89]  Arild Nøkland,et al.  Training Neural Networks with Local Error Signals , 2019, ICML.

[90]  Erich Elsen,et al.  Efficient Neural Audio Synthesis , 2018, ICML.

[91]  J. F. Kolen,et al.  Backpropagation without weight transport , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[92]  Wolfgang Maass,et al.  Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes , 2020, Nature Machine Intelligence.

[93]  Xiaohui Xie,et al.  Learning Curves for Stochastic Gradient Descent in Linear Feedforward Networks , 2003, Neural Computation.

[94]  Malu Zhang,et al.  An Efficient and Perceptually Motivated Auditory Neural Encoding and Decoding Algorithm for Spiking Neural Networks , 2019, Frontiers in Neuroscience.

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

[96]  Nicholas T. Carnevale,et al.  Simulation of networks of spiking neurons: A review of tools and strategies , 2006, Journal of Computational Neuroscience.

[97]  Gert Cauwenberghs,et al.  Large-Scale Neuromorphic Spiking Array Processors: A Quest to Mimic the Brain , 2018, Front. Neurosci..

[98]  Bjorn De Sutter,et al.  Dynamic Automatic Differentiation of GPU Broadcast Kernels , 2018, NIPS 2018.

[99]  Sander M. Bohte,et al.  Efficient Computation in Adaptive Artificial Spiking Neural Networks , 2017, ArXiv.

[100]  Friedemann Zenke,et al.  Finding trainable sparse networks through Neural Tangent Transfer , 2020, ICML.

[101]  Stefan Wermter,et al.  Continual Lifelong Learning with Neural Networks: A Review , 2019, Neural Networks.

[102]  André Grüning,et al.  Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding , 2016, PloS one.

[103]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[104]  Moritz Hardt,et al.  Stable Recurrent Models , 2018, ICLR.

[105]  U. Bhalla Molecular computation in neurons: a modeling perspective , 2014, Current Opinion in Neurobiology.

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

[107]  Carver Mead,et al.  Analog VLSI and neural systems , 1989 .

[108]  Surya Ganguli,et al.  Continual Learning Through Synaptic Intelligence , 2017, ICML.

[109]  Wulfram Gerstner,et al.  Limits to high-speed simulations of spiking neural networks using general-purpose computers , 2014, Front. Neuroinform..

[110]  Daniel L. K. Yamins,et al.  Pruning neural networks without any data by iteratively conserving synaptic flow , 2020, NeurIPS.

[111]  W. Gerstner,et al.  Temporal whitening by power-law adaptation in neocortical neurons , 2013, Nature Neuroscience.

[112]  Jacques Kaiser,et al.  Synaptic Plasticity Dynamics for Deep Continuous Local Learning (DECOLLE) , 2018, Frontiers in Neuroscience.

[113]  James M Murray,et al.  Local online learning in recurrent networks with random feedback , 2018, bioRxiv.

[114]  Alex Graves,et al.  Supervised Sequence Labelling , 2012 .

[115]  Henry Kennedy,et al.  A Predictive Network Model of Cerebral Cortical Connectivity Based on a Distance Rule , 2013, Neuron.

[116]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[117]  Terrence J. Sejnowski,et al.  Gradient Descent for Spiking Neural Networks , 2017, NeurIPS.

[118]  A. Litwin-Kumar,et al.  Formation and maintenance of neuronal assemblies through synaptic plasticity , 2014, Nature Communications.

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

[120]  David Kappel,et al.  Deep Rewiring: Training very sparse deep networks , 2017, ICLR.

[121]  Wulfram Gerstner,et al.  Stochastic variational learning in recurrent spiking networks , 2014, Front. Comput. Neurosci..

[122]  Angelika Steger,et al.  Approximating Real-Time Recurrent Learning with Random Kronecker Factors , 2018, NeurIPS.

[123]  Alex Graves,et al.  Supervised Sequence Labelling with Recurrent Neural Networks , 2012, Studies in Computational Intelligence.

[124]  Yannik Stradmann,et al.  Training spiking multi-layer networks with surrogate gradients on an analog neuromorphic substrate , 2020, ArXiv.

[125]  Eugene M. Izhikevich,et al.  Dynamical Systems in Neuroscience: The Geometry of Excitability and Bursting , 2006 .

[126]  Antoine Dupret,et al.  SpikeGrad: An ANN-equivalent Computation Model for Implementing Backpropagation with Spikes , 2019, ICLR.

[127]  L. F. Abbott,et al.  Generating Coherent Patterns of Activity from Chaotic Neural Networks , 2009, Neuron.

[128]  James Martens,et al.  On the Variance of Unbiased Online Recurrent Optimization , 2019, ArXiv.

[129]  Evangelos Eleftheriou,et al.  Deep learning incorporating biologically inspired neural dynamics and in-memory computing , 2020, Nature Machine Intelligence.

[130]  Yann Ollivier,et al.  Unbiased Online Recurrent Optimization , 2017, ICLR.

[131]  Peter C. Humphreys,et al.  Deep Learning without Weight Transport , 2019, NeurIPS.