Learning of spatiotemporal patterns in a spiking neural network with resistive switching synapses

Resistive switching devices were used as technological synapses to learn about the spatial- and temporal-correlated neuron spikes. The human brain is a complex integrated spatiotemporal system, where space (which neuron fires) and time (when a neuron fires) both carry information to be processed by cognitive functions. To parallel the energy efficiency and computing functionality of the brain, methodologies operating over both the space and time domains are thus essential. Implementing spatiotemporal functions within nanoscale devices capable of synaptic plasticity would contribute a significant step toward constructing a large-scale neuromorphic system that emulates the computing and energy performances of the human brain. We present a neuromorphic approach to brain-like spatiotemporal computing using resistive switching synapses. To process the spatiotemporal spike pattern, time-coded spikes are reshaped into exponentially decaying signals that are fed to a McCulloch-Pitts neuron. Recognition of spike sequences is demonstrated after supervised training of a multiple-neuron network with resistive switching synapses. Finally, we show that, due to the sensitivity to precise spike timing, the spatiotemporal neural network is able to mimic the sound azimuth detection of the human brain.

[1]  Ryad Benosman,et al.  A spiking neural network model of 3D perception for event-based neuromorphic stereo vision systems , 2017, Scientific Reports.

[2]  Pritish Narayanan,et al.  Equivalent-accuracy accelerated neural-network training using analogue memory , 2018, Nature.

[3]  Simone Balatti,et al.  A 2-transistor/1-resistor artificial synapse capable of communication and stochastic learning in neuromorphic systems , 2015, Front. Neurosci..

[4]  Malu Zhang,et al.  Efficient training of supervised spiking neural networks via the normalized perceptron based learning rule , 2017, Neurocomputing.

[5]  Rémi Monasson,et al.  Theory of spike timing-based neural classifiers. , 2010, Physical review letters.

[6]  S. Ambrogio,et al.  Analytical Modeling of Oxide-Based Bipolar Resistive Memories and Complementary Resistive Switches , 2014, IEEE Transactions on Electron Devices.

[7]  E. Eleftheriou,et al.  All-memristive neuromorphic computing with level-tuned neurons , 2016, Nanotechnology.

[8]  Fred J. Damerau,et al.  A technique for computer detection and correction of spelling errors , 1964, CACM.

[9]  M. Häusser.  The Hodgkin-Huxley theory of the action potential , 2000, Nature Neuroscience.

[10]  S. Thorpe,et al.  Spike times make sense , 2005, Trends in Neurosciences.

[11]  Sergey L. Gratiy,et al.  Fully integrated silicon probes for high-density recording of neural activity , 2017, Nature.

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

[13]  Charles Kemp,et al.  How to Grow a Mind: Statistics, Structure, and Abstraction , 2011, Science.

[14]  Fabien Alibart,et al.  Pattern classification by memristive crossbar circuits using ex situ and in situ training , 2013, Nature Communications.

[15]  A. Calderoni,et al.  Performance comparison of O-based and Cu-based ReRAM for high-density applications , 2014, 2014 IEEE 6th International Memory Workshop (IMW).

[16]  Robert Gütig,et al.  To spike, or when to spike? , 2014, Current Opinion in Neurobiology.

[17]  Peng Lin,et al.  Fully memristive neural networks for pattern classification with unsupervised learning , 2018 .

[18]  D. Ielmini,et al.  Demonstration of hybrid CMOS/RRAM neural networks with spike time/rate-dependent plasticity , 2016, 2016 IEEE International Electron Devices Meeting (IEDM).

[19]  Sidney B. Williams,et al.  Differential modulation of repetitive firing and synchronous network activity in neocortical interneurons by inhibition of A-type K+ channels and Ih , 2015, Front. Cell. Neurosci..

[20]  Alessandro Calderoni,et al.  Neuromorphic Learning and Recognition With One-Transistor-One-Resistor Synapses and Bistable Metal Oxide RRAM , 2016, IEEE Transactions on Electron Devices.

[21]  Walter Senn,et al.  Learning Real-World Stimuli in a Neural Network with Spike-Driven Synaptic Dynamics , 2007, Neural Computation.

[22]  Wolfgang Maass,et al.  Networks of Spiking Neurons: The Third Generation of Neural Network Models , 1996, Electron. Colloquium Comput. Complex..

[23]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[24]  Malu Zhang,et al.  Supervised learning in spiking neural networks with noise-threshold , 2017, Neurocomputing.

[25]  Thomas P. Parnell,et al.  Temporal correlation detection using computational phase-change memory , 2017, Nature Communications.

[26]  Stefano Panzeri,et al.  Distinct timescales of population coding across cortex , 2017, Nature.

[27]  Huaqiang Wu,et al.  An artificial nociceptor based on a diffusive memristor , 2018, Nature Communications.

[28]  G. Silberberg,et al.  Measurement and analysis of postsynaptic potentials using a novel voltage-deconvolution method. , 2008, Journal of neurophysiology.

[29]  Paolo Fantini,et al.  Unsupervised Learning by Spike Timing Dependent Plasticity in Phase Change Memory (PCM) Synapses , 2016, Front. Neurosci..

[30]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[31]  J Joshua Yang,et al.  Memristive devices for computing. , 2013, Nature nanotechnology.

[32]  Brice Bathellier,et al.  Temporal asymmetries in auditory coding and perception reflect multi-layered nonlinearities , 2016, Nature Communications.

[33]  Andrzej J. Kasinski,et al.  Supervised Learning in Spiking Neural Networks with ReSuMe: Sequence Learning, Classification, and Spike Shifting , 2010, Neural Computation.

[34]  B. Delgutte,et al.  A Physiologically Based Model of Interaural Time Difference Discrimination , 2004, The Journal of Neuroscience.

[35]  Alexander Borst,et al.  Information theory and neural coding , 1999, Nature Neuroscience.

[36]  Wofgang Maas,et al.  Networks of spiking neurons: the third generation of neural network models , 1997 .

[37]  Jiaming Zhang,et al.  Analogue signal and image processing with large memristor crossbars , 2017, Nature Electronics.

[38]  Gregory V. Bard,et al.  Spelling-Error Tolerant, Order-Independent Pass-Phrases via the Damerau-Levenshtein String-Edit Distance Metric , 2007, ACSW.

[39]  Huajin Tang,et al.  Precise-Spike-Driven Synaptic Plasticity: Learning Hetero-Association of Spatiotemporal Spike Patterns , 2013, PloS one.

[40]  Claudia Clopath,et al.  Modeling somatic and dendritic spike mediated plasticity at the single neuron and network level , 2017, Nature Communications.

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

[42]  Heiner Giefers,et al.  Mixed-precision in-memory computing , 2017, Nature Electronics.

[43]  Daniele Ielmini,et al.  Resistive switching memories based on metal oxides: mechanisms, reliability and scaling , 2016 .

[44]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[45]  Steven M. Peterson,et al.  A spatiotemporal coding mechanism for background-invariant odor recognition , 2013, Nature Neuroscience.

[46]  Farnood Merrikh-Bayat,et al.  Training and operation of an integrated neuromorphic network based on metal-oxide memristors , 2014, Nature.

[47]  A S Spinelli,et al.  Memristive neural network for on-line learning and tracking with brain-inspired spike timing dependent plasticity , 2017, Scientific Reports.

[48]  Catherine E. Graves,et al.  Memristor‐Based Analog Computation and Neural Network Classification with a Dot Product Engine , 2018, Advanced materials.

[49]  Wei D. Lu,et al.  Sparse coding with memristor networks. , 2017, Nature nanotechnology.

[50]  J. Yang,et al.  Memristors with diffusive dynamics as synaptic emulators for neuromorphic computing. , 2017, Nature materials.

[51]  John F. Roddick,et al.  Proceedings of the fifth Australasian symposium on ACSW frontiers - Volume 68 , 2007 .

[52]  E. Vianello,et al.  HfO2-Based OxRAM Devices as Synapses for Convolutional Neural Networks , 2015, IEEE Transactions on Electron Devices.