Applications of an algorithm that mimics cortical processing

Details Applications of an algorithm that mimics cortical processing Applications of an algorithm that mimics cortical processing

2004-06-02

2008-09-30

Hirl, Joseph P. (Department: 2129)

Data processing: artificial intelligence

Neural network

Learning task

C706S014000, C706S015000, C706S035000, C706S041000, C706S043000

Reexamination Certificate

active

07430546

ABSTRACT:
An information processing system having neuron-like signal processors that are interconnected by synapse-like processing junctions that simulates and extends capabilities of biological neural networks. The information processing systems uses integrate-and-fire neurons and Temporally Asymmetric Hebbian learning (spike timing-dependent learning) to adapt the synaptic strengths. The synaptic strengths of each neuron are guaranteed to become optimal during the course of learning either for estimating the parameters of a dynamic system (system identification) or for computing the first principal component. This neural network is well-suited for hardware implementations, since the learning rule for the synaptic strengths only requires computing either spike-time differences or correlations. Such hardware implementation may be used for predicting and recognizing audiovisual information or for improving cortical processing by a prosthetic device.

REFERENCES:
patent: 5706402 (1998-01-01), Bell
patent: 6358281 (2002-03-01), Berrang et al.
patent: 6363369 (2002-03-01), Liaw et al.
patent: 6643627 (2003-11-01), Liaw et al.
Sander Bothe, Spiking Neural Networks, Mar. 2003, Thesis, Centre for Computer Science and Mathematics, 1-129.
Kunkle et al. “Pulsed Neural NEtworks and Their Applications”, 2002, pp. 1-11.
Bothe Sander “Spiking Neural Networks”, 2003, pp. 1-129.
Kunkle et al. “Pulsed Neural Networks and their Applications”, 2002, pp. 1-11□□.
Wulfram, “Spiking Neurons”, pp. 3-54.
August DA, Levy WB. Temporal sequence compression by an integrate-and-fire model of hippocampal area CA3. J Comput Neurosci 6, 1: 71-90 (1999).
Baldi P. F. and Hornik K., “Learning in Linear Neural Networks: A Survey”, IEEE Trans. ASSP 6: 837-858 (1995).
Bi Guo-qiang and Poo Mu-ming. Distributed synaptic modification in neural networks induced by patterned stimulation. Nature 401, 792-796, (1999).
Gerstner W. and Abbott L. F. Learning navigational maps through potentiation and modulation of hippocampal place cells. J Comput Neurosci 4 (1), 79-94 (1997).
Gerstner W, Kistler WM. Mathematical formulations of Hebbian Learning. Biol Cybern, 87, 5-6: 404-415 (2002).
Himberg and A. Hyvärinen. Independent component analysis for binary data: An experimental study . In Proc. Int. Workshop on Independent Component Analysis and Blind Signal Separation (ICA2001), San Diego, California, pp. 552-556 (2001).
Hyvärinen A. and Oja E. Independent Component Analysis by General Non-linear Hebbian-like Learning Rules. Signal Processing, 64(3):301-313 (1998).
Oja, E. Principle components, minor components, and linear neural networks, Neural Networks, vol. 5, pp. 927-935 (1992).
Oja E., Karhunen J., Wang L., and Vigario R. “Principal and independent components in neural networks—Recent developments,” in Proc.VII Italian Wkshp. Neural Nets WIRN'95, Vietri sul Mare, Italy (1995).
Pfister J.-P., Barber D., Gerstner W.: Optimal Hebbian Learning: A Probabilistic Point of View. ICANN/ICONIP 2003, Istanbul, Turkey, Jun. 26-29: 92-98 (2003).
Rao RP, Sejnowksi TJ Spike-timing-dependent Hebbian plasticity as temporal difference learning. Neural Comput 13, 10: 2221-2237 (2001).
Roberts PD, Bell CC. Computational consequences of temporally asymmetric learning rules: II. Sensory image cancellation. J Comput Neurosci. ;9(1):67-83 (2000).
Roberts PD, Bell CC. Spike timing dependent synaptic plasticity in biological systems. Biol Cybern. ;87(5-6):392-403 (2002).
Rubin, J., Lee, D. D., Sompolinsky, The Equilibrium Properties of Temporally Asymmetric Hebbian Plasticity. H. Phys Rev Lett. 86 (2): 364-7 (2001).
Suri R.E., Sejnowski T.J.. Spike propagation synchronized by temporally asymmetric Hebbian learning. Biol Cybern.87(5-6):440-5, (2002).
Williams A, Roberts PD, Leen TK. Stability of negative-image equilibria in spike-timing-dependent plasticity. Phys Rev E Stat Nonlin Soft Matter Phys. (Aug. 2003); 68(2 Pt 1):021923. Epub (Aug. 29, 2003).
Williams R.J., Peng J. An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories, Neural Computation, 2, 490-501 (1990).
Zuo L., Wang Y., Tan T., PCA-Based Personal Handwriting Identification, International Conference on Image and Graphics ICIG, (2002).
Porr B, Worgotter F. Isotropic sequence order learning. Neural Comput. Apr. 2003;15(4):831-64.

Affiliated with

Also associated with

Rating

Applications of an algorithm that mimics cortical processing does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Applications of an algorithm that mimics cortical processing, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Applications of an algorithm that mimics cortical processing will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3987867