×

CMOL implementation of spiking neurons and spike-timing dependent plasticity. (English) Zbl 1221.68187

Summary: Successful implementation of spiking neural networks onto CMOS-Molecular (CMOL) architecture has already been proposed, but the ability of dynamic learning has not yet been addressed. Here, we propose a spiking neural topology with spike-timing-dependent learning ability and provide its basic building blocks that are easily mapped onto CMOL architecture. The learning method modifies state of synaptic switches, using spatially and temporally local information which is available at the synapse when state modification is performed.
The performance of the proposed topology is analyzed with regards to pre- and post-synaptic spike timing, and simulation results are provided for a synapse with spike-timing-dependent plasticity properties. Furthermore, its performance as spike-timing correlation learning and synchrony detection in a small feed-forward network is demonstrated as a case example.

MSC:

68T05 Learning and adaptive systems in artificial intelligence

Software:

CrossNets
PDF BibTeX XML Cite
Full Text: DOI

References:

[1] Strukov, Introducing Molecular Electronics pp 447– (2005)
[2] Snider, Self-organized computation with unreliable, memristive nanodevices, Nanotechnology 18 pp 365202– (2007)
[3] DeHon, Nanowire-based programmable architectures, ACM Journal on Emerging Technologies in Computing Systems 1 pp 109– (2005)
[4] Snider, Nano/CMOS architectures using a field-programmable nanowire interconnect, Nanotechnology 18 (2007)
[5] Strukov, CMOL FPGA: a reconfigurable architecture for hybrid digital circuits with two-terminal nanodevices, Nanotechnology 16 pp 888– (2005)
[6] Masoumi, Design and evaluation of basic standard encryption algorithm modules using nanosized complementary metal-oxide-semiconductor-molecular circuits, Nanotechnology 17 pp 89– (2006)
[7] Strukov, Prospects for terabit-scale nanoelectronic memories, Nanotechnology 16 pp 137– (2005)
[8] Turel, Neuromorphic architectures for nanoelectronic circuits, International Journal of Circuit Theory and Application 32 pp 277– (2004)
[9] Lee, Defect-tolerant nanoelectronic pattern classifiers, International Journal of Circuit Theory and Applications 35 pp 239– (2007)
[10] Wagner, Analysis of the interaction between the retinal ON and OFF channels using CNN-UM models, International Journal of Circuit Theory and Applications 37 pp 87– (2009)
[11] Rák, Stochastic bitstream-based CNN and its implementation on FPGA, International Journal of Circuit Theory and Applications 37 (4) pp 587– (2009) · Zbl 1191.94158
[12] Zhang W Wu NJ CMOL-based Cellular Neural Networks and Parallel Processor for Future Image processing 737 740
[13] Indiveri, A VLSI array of low-power spiking neurons and bistable synapses with spike-timing dependent plasticity, IEEE Transactions on Neural Networks 17 pp 211– (2006)
[14] Hoekstra, Towards a circuit theory for metallic single-electron tunnelling devices, International Journal of Circuit Theory and Applications 35 pp 213– (2007)
[15] Csurgay, On circuit models for quantum-classical networks, International Journal of Circuit Theory and Applications 35 (5-6) pp 471– (2007) · Zbl 1130.81317
[16] Gao, Cortical models onto CMOL and CMOS-architectures and performance/price, IEEE Transactions on Circuits and Systems 54 pp 2502– (2007) · Zbl 1374.94947
[17] Snider GS Spike-timing-dependent learning in memris-tive nanodevices 85 92
[18] Afifi, STDP implemen-tation using memristive nanodevice in CMOS-Nano neuromorphic networks, IEICE Electronics Express 6 (3) pp 148– (2009)
[19] Gorchetchnikov, A model of STDP based on spatially and temporally local information: derivation and combination with gated decay, Neural Networks 18 pp 458– (2005) · Zbl 1077.68764
[20] Maass, Networks of spiking neurons: the third generation of neural network models, Neural Networks 10 pp 1659– (1997)
[21] Gerstner, Spiking Neuron Models: Single Neurons, Populations, Plasticity (2002) · Zbl 1100.92501
[22] Maass, On the computational power of recurrent circuits of spiking neurons, Journal of Computer and System Sciences 69 pp 593– (2004) · Zbl 1076.68062
[23] Ravinuthula, Time-mode circuits for analog computation, International Journal of Circuit Theory and Applications 37 (5) pp 631– (2009) · Zbl 1191.94024
[24] Izhikevich, Which model to use for cortical spiking neurons, IEEE Transactions on Neural Network 15 pp 1063– (2004)
[25] Sasaki, A VLSI spiking feedback neural network with negative thresholding and its application to associative memory, IEICE Transactions on Electronics E89-C pp 1637– (2006)
[26] Chicca, A VLSI recurrent network of integrate-and-fire neurons connected by plastic synapses with long-term memory, IEEE Transactions on Neural Networks 14 pp 1297– (2003)
[27] Hebb, Reprinted in Neurocomputing, Foundations of Research 1949 pp 60– (1988)
[28] Grossberg, Classical and instrumental conditioning by neural networks, Progress in Theoretical Biology 3 pp 51– (1974)
[29] Debanne, Long-term synaptic plasticity between pairs of individual CA3 pyramidal cells in rat hippocampal slice cultures, Journal of Physiology 507 pp 237– (1998)
[30] Kistler, Modeling synaptic plasticity in conjunction with the timing of pre- and post-synaptic action potentials, Neural Computation 12 pp 385– (2000)
[31] Song, Competitive Hebbian learning through spike-timing dependent synaptic plasticity, Nature Neuroscience 3 pp 919– (2000)
[32] Bi, Activity-induced synaptic modifi-cations in hippocampal culture: dependence on spike timing, synaptic strength and cell type, Journal of Neuroscience 18 pp 10464– (1998)
[33] Markram, Regulation of synaptic efficacy by coincidence of postsynaptic AP’s and EPSPs, Science 275 pp 213– (1997)
[34] Vogelstein, Proceedings of the NIPS’03 pp 15– (2003)
[35] Saudargiene, How the shape of pre- and post-synaptic signals can influence STDP: a biophysical model, Neural Computation 16 pp 595– (2004) · Zbl 1050.92012
[36] Turel, CrossNets: possible neuromorphic networks based on nanoscale components, International Journal of Circuit Theory and Applications 31 pp 37– (2003) · Zbl 1016.94045
[37] Lee JH Likharev KK CMOL crossNets as pattern classifiers 2005 446 454
[38] Gerstner, Pulsed Neural Networks pp 353– (1999)
[39] Chen A Haddad S Wu YC Fang TN Lan Z Avanzino S Pangrle S Buynoski M Rathor M Cai W Tripsas N Bill C VanBuskirk M Taguchi M Non-volatile resistive switching for advanced memory applications 746 749
[40] Izhikevich, Relating STDP to BCM, Neural Computation 15 pp 1511– (2003) · Zbl 1109.92307
[41] Mozsary, Function-in-layout: a demonstration with bio-inspired hyperacuity chip, International Journal of Circuit Theory and Applications 35 pp 149– (2007)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.