IIAE CONFERENCE SYSTEM, The 1st IEEE/IIAE International Conference on Intelligent Systems and Image Processing 2013 (ICISIP2013)

Font Size: 
Hebbian Learning in FPGA Silicon Neuronal Network
Jing Li, Yuichi Katori, Takashi Kohno

Last modified: 2013-10-01

Abstract


This paper describes a digital silicon neuronal network trained by the Hebbian learning rule that can execute the auto-associative memory. In our previous work, a fully connected network of 256 silicon neurons based on the digital spiking silicon neuron (DSSN) model and kinetic-model-based silicon synapses were implemented. In this work, we added circuit modules that append Hebbian learning function and fitted it to a Xilinx Virtex 6 XC6VSX315T FPGA device. The performances of auto-associative memory with several spike-time-dependent Hebbian learning rules and the correlation rule are compared. The results show that Hebbian learning rules that model both synaptic potentiation and depression improve the retrieval probability in our silicon neuronal network.

Keywords


Hebbian learning, silicon neuronal network, FPGA, associative memory

References


(1) Cline H.T., Constantine-Paton, M. and Debski., E : “Patterned activity, synaptic convergence and the NMDA receptor in developing visual pathways”, Neurosci., 13, 129–154, 1990

(2) Caillard O. Gaiarsa, J.L. and Y. Ben-Ari. : “Long-term plasticity at gabaergic and glycinergic synapses: mechanisms and functional significance”, Trends Neurosci., 25, 564–570, 2002

(3) T.V. Bliss and G.L. Collingridge. : “Synaptic model of memory: long-term potentiation in the hippocampus”, Nature, 361, 31–39, 1993

(4) Burke J.P. Smith-D. Fregnac, Y. and M.J. Friedlander. : “Temporal covariance of pre and postsynaptic activity regulates functional connectivity in the visual cortex”, J. Neurophysiol., 71, 1403–1421, 1994

(5) Hebb, D. O : “Organization of Behavior” John Wiley & Sons, New York. 1949

(6) Wulfram Gerstner and Werner M.Kistler : “Spiking neuron models single neurons, populations, plasticity”, Cambridge university press, 2002

(7) James, Ting-Ho Lo : “Unsupervised Hebbian learning by recurrent multilayer neural networks for temporal hierarchical pattern recognition”, Annual Conference on Information Sciences and Systems (CISS), 1–6, 2010

(8) Oniga, S., Tisan, A., Mic, D., Buchman A. and Vida-Ratiu, A. : “Optimizing FPGA Implementation of Feed-Forward Neural Networks”, International Conference on Optimization of Electrical and Electronic Equipment (OPTIM), 31-36, 2008

(9) Andrés Upegui, Carlos Andrés Peña-Reyes, Eduardo Sánchez : “A hardware implementation of a network of functional spiking neurons with Hebbian learning”, Biologically Inspired Approaches to Advanced Information Technology, Springer Berlin Heidelberg, 233-243, 2004

(10) H. Kolle Riis and P. Hafliger : “spike based learning with weak multi-level static memory”, International Symposium on Circuits and Systems (ISCAS), 5,393-396, 2004

(11) John Rinzel and Bard Ermentrout : “Analysis of excitability and oscillations”, Methods in neuronal modeling, MIT Press, 1989

(12) Takashi Kohno and Kazuyuki Aihara : “Digital spiking silicon neuron: concept and behaviors in GJ-coupled network”, International Symposium on Artificial Life and Robotics, OS3-6, 2007

(13) Jing Li, Yuichi Katori and Takashi Kohno : “An FPGA-based silicon neuronal network with selectable excitability silicon neurons”, Frontiers in neuroscience, 6, 183, 2012

(14) Hodgkin, A.L. : “The local electric changes associated with repetitive action in a non-medullated axon”, J. Physiol., 107, 165-181, 1948

(15) Hopfield, J.J. : “Neural networks and physical systems with emergent collective computational abilities”, Proc. Natl. Acad. Sci., 79, 2254-2258, 1982

(16) Tsodyks, M.B. : “Associative memory in neural networks with the Hebbian learning rule”, Modern Physics Letters B, 3, 555-560, 1989

(17) Molter, C., Salihoglu, U. and Bersini, H. : “Learning cycles brings chaos in continuous hopfield networks”, IJCNN, 2, 770-775, 2005

(18) Chen, J., Liu, Y., Chen, Q. and Cui, J. : “A neural network model for concept formation”, ICNC, 3, 24-28, 2008


Full Text: PDF