Tags

Type your tag names separated by a space and hit enter

A compound memristive synapse model for statistical learning through STDP in spiking neural networks.
Front Neurosci 2014; 8:412FN

Abstract

Memristors have recently emerged as promising circuit elements to mimic the function of biological synapses in neuromorphic computing. The fabrication of reliable nanoscale memristive synapses, that feature continuous conductance changes based on the timing of pre- and postsynaptic spikes, has however turned out to be challenging. In this article, we propose an alternative approach, the compound memristive synapse, that circumvents this problem by the use of memristors with binary memristive states. A compound memristive synapse employs multiple bistable memristors in parallel to jointly form one synapse, thereby providing a spectrum of synaptic efficacies. We investigate the computational implications of synaptic plasticity in the compound synapse by integrating the recently observed phenomenon of stochastic filament formation into an abstract model of stochastic switching. Using this abstract model, we first show how standard pulsing schemes give rise to spike-timing dependent plasticity (STDP) with a stabilizing weight dependence in compound synapses. In a next step, we study unsupervised learning with compound synapses in networks of spiking neurons organized in a winner-take-all architecture. Our theoretical analysis reveals that compound-synapse STDP implements generalized Expectation-Maximization in the spiking network. Specifically, the emergent synapse configuration represents the most salient features of the input distribution in a Mixture-of-Gaussians generative model. Furthermore, the network's spike response to spiking input streams approximates a well-defined Bayesian posterior distribution. We show in computer simulations how such networks learn to represent high-dimensional distributions over images of handwritten digits with high fidelity even in presence of substantial device variations and under severe noise conditions. Therefore, the compound memristive synapse may provide a synaptic design principle for future neuromorphic architectures.

Authors+Show Affiliations

Faculty of Computer Science and Biomedical Engineering, Institute for Theoretical Computer Science, University of Technology Graz, Austria.Faculty of Computer Science and Biomedical Engineering, Institute for Theoretical Computer Science, University of Technology Graz, Austria.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

25565943

Citation

Bill, Johannes, and Robert Legenstein. "A Compound Memristive Synapse Model for Statistical Learning Through STDP in Spiking Neural Networks." Frontiers in Neuroscience, vol. 8, 2014, p. 412.
Bill J, Legenstein R. A compound memristive synapse model for statistical learning through STDP in spiking neural networks. Front Neurosci. 2014;8:412.
Bill, J., & Legenstein, R. (2014). A compound memristive synapse model for statistical learning through STDP in spiking neural networks. Frontiers in Neuroscience, 8, p. 412. doi:10.3389/fnins.2014.00412.
Bill J, Legenstein R. A Compound Memristive Synapse Model for Statistical Learning Through STDP in Spiking Neural Networks. Front Neurosci. 2014;8:412. PubMed PMID: 25565943.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - A compound memristive synapse model for statistical learning through STDP in spiking neural networks. AU - Bill,Johannes, AU - Legenstein,Robert, Y1 - 2014/12/16/ PY - 2014/09/30/received PY - 2014/11/24/accepted PY - 2015/1/8/entrez PY - 2015/1/8/pubmed PY - 2015/1/8/medline KW - Bayesian inference KW - STDP KW - WTA KW - memristor KW - neuromorphic KW - synapse KW - synaptic plasticity KW - unsupervised learning SP - 412 EP - 412 JF - Frontiers in neuroscience JO - Front Neurosci VL - 8 N2 - Memristors have recently emerged as promising circuit elements to mimic the function of biological synapses in neuromorphic computing. The fabrication of reliable nanoscale memristive synapses, that feature continuous conductance changes based on the timing of pre- and postsynaptic spikes, has however turned out to be challenging. In this article, we propose an alternative approach, the compound memristive synapse, that circumvents this problem by the use of memristors with binary memristive states. A compound memristive synapse employs multiple bistable memristors in parallel to jointly form one synapse, thereby providing a spectrum of synaptic efficacies. We investigate the computational implications of synaptic plasticity in the compound synapse by integrating the recently observed phenomenon of stochastic filament formation into an abstract model of stochastic switching. Using this abstract model, we first show how standard pulsing schemes give rise to spike-timing dependent plasticity (STDP) with a stabilizing weight dependence in compound synapses. In a next step, we study unsupervised learning with compound synapses in networks of spiking neurons organized in a winner-take-all architecture. Our theoretical analysis reveals that compound-synapse STDP implements generalized Expectation-Maximization in the spiking network. Specifically, the emergent synapse configuration represents the most salient features of the input distribution in a Mixture-of-Gaussians generative model. Furthermore, the network's spike response to spiking input streams approximates a well-defined Bayesian posterior distribution. We show in computer simulations how such networks learn to represent high-dimensional distributions over images of handwritten digits with high fidelity even in presence of substantial device variations and under severe noise conditions. Therefore, the compound memristive synapse may provide a synaptic design principle for future neuromorphic architectures. SN - 1662-4548 UR - https://www.unboundmedicine.com/medline/citation/25565943/A_compound_memristive_synapse_model_for_statistical_learning_through_STDP_in_spiking_neural_networks_ L2 - https://doi.org/10.3389/fnins.2014.00412 DB - PRIME DP - Unbound Medicine ER -