Unsupervised, supervised and reinforced learning via spiking computation
Abstract
The present invention relates to unsupervised, supervised and reinforced learning via spiking computation. The neural network comprises a plurality of neural modules. Each neural module comprises multiple digital neurons such that each neuron in a neural module has a corresponding neuron in another neural module. An interconnection network comprising a plurality of edges interconnects the plurality of neural modules. Each edge interconnects a first neural module to a second neural module, and each edge comprises a weighted synaptic connection between every neuron in the first neural module and a corresponding neuron in the second neural module.
- Inventors:
- Issue Date:
- Research Org.:
- International Business Machines Corp., Armonk, NY (United States)
- Sponsoring Org.:
- USDOE; Defense Advanced Research Projects Agency (DARPA)
- OSTI Identifier:
- 1986744
- Patent Number(s):
- 11481621
- Application Number:
- 16/543,311
- Assignee:
- International Business Machines Corporation (Armonk, NY)
- DOE Contract Number:
- HR0011-09-C-0002
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 08/16/2019
- Country of Publication:
- United States
- Language:
- English
Citation Formats
Modha, Dharmendra S. Unsupervised, supervised and reinforced learning via spiking computation. United States: N. p., 2022.
Web.
Modha, Dharmendra S. Unsupervised, supervised and reinforced learning via spiking computation. United States.
Modha, Dharmendra S. Tue .
"Unsupervised, supervised and reinforced learning via spiking computation". United States. https://www.osti.gov/servlets/purl/1986744.
@article{osti_1986744,
title = {Unsupervised, supervised and reinforced learning via spiking computation},
author = {Modha, Dharmendra S.},
abstractNote = {The present invention relates to unsupervised, supervised and reinforced learning via spiking computation. The neural network comprises a plurality of neural modules. Each neural module comprises multiple digital neurons such that each neuron in a neural module has a corresponding neuron in another neural module. An interconnection network comprising a plurality of edges interconnects the plurality of neural modules. Each edge interconnects a first neural module to a second neural module, and each edge comprises a weighted synaptic connection between every neuron in the first neural module and a corresponding neuron in the second neural module.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2022},
month = {10}
}
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Systems, methods and computer program products for supervised dimensionality reduction with mixed-type features and labels
patent, August 2011
- Grabarnik, Genady; Rish, Irina
- US Patent Document 7,996,342
Information recognition system and control system using same
patent, April 1997
- Shinohara, Wataro; Takagi, Yasuo; Iino, Yutaka
- US Patent Document 5,619,619
Lock-free state merging in parallelized constraint satisfaction problem solvers
patent, June 2009
- Brown, Allen
- US Patent Document 7,543,266
Reconfigurable and customizable general-purpose circuits for neural networks
patent, October 2014
- Brezzo, Bernard V.; Chang, Leland; Esser, Steven K.
- US Patent Document 8,856,055
Applications of an algorithm that mimics cortical processing
patent, September 2008
- Suri, Roland
- US Patent Document 7,430,546
Event-Driven Universal Neural Network Circuit
patent-application, June 2016
- Modha, Dharmendra S.
- US Patent Application 15/015990; 20160162780
Interactive configuration of connectivity in schematic diagram of integrated circuit design
patent, June 2012
- Goh, Denis Chuan Hu; Ong, Goet Kwone; Chew, Chai Pin
- US Patent Document 8,205,183
Unsupervised, Supervised and Reinforced Learning Via Spiking Computation
patent-application, December 2019
- Modha, Dharmendra S.
- US Patent Application 16/543311; 20190370655
Multi-Modal Neural Network for Universal, Online Learning
patent-application, July 2019
- Modha, Dharmendra S.
- US Patent Application 16/289488; 20190205754
Modulated Exploratory Dynamics can Shape Self-Organized Behavior
journal, June 2009
- Hesse, Frank; Der, Ralf; Herrmann, J. Michael
- Advances in Complex Systems, Vol. 12, Issue 03
Unsupervised, Supervised and Reinforced Learning Via Spiking Computation
patent-application, July 2017
- Modha, Dharmendra S.
- US Patent Application 15/162361; 20170213133
Support Vector Machines in a Relational Database Management System
patent-application, March 2005
- Melenova, Boriana L.; Yarmus, Joseph S.; Campos, Marcos M.
- US Patent Application 10/927024; 20050050087
Complex brain networks: graph theoretical analysis of structural and functional systems
journal, February 2009
- Bullmore, Ed; Sporns, Olaf
- Nature Reviews Neuroscience, Vol. 10, Issue 3
Facet classification neural network
patent, December 2000
- Brady, Mark J.; Million, Belayneh W.; Strand, John T.
- US Patent Document 6,167,390
Spiking Dynamical Neural Network for Parallel Prediction of Multiple Temporal Events
patent-application, July 2010
- Srinivasa, Narayan; Cho, Youngkwan; Barajas, Leandro G.
- US Patent Application 12/353031; 20100179935
Dynamic Hebbian learning in adaptive frequency oscillators
journal, April 2006
- Righetti, Ludovic; Buchli, Jonas; Ijspeert, Auke Jan
- Physica D: Nonlinear Phenomena, Vol. 216, Issue 2
Fuzzy lattice neural network (FLNN): a hybrid model for learning
journal, January 1998
- Petridis, V.; Kaburlasos, V. G.
- IEEE Transactions on Neural Networks, Vol. 9, Issue 5
Event-Driven Universal Neural Network Circuit
patent-application, October 2017
- Modha, Dharmendra S.
- US Patent Application 15/280047; 20170308788
Implementing spike-timing-dependent plasticity on SpiNNaker neuromorphic hardware
conference, July 2010
- Jin, Xin; Rast, Alexander; Galluppi, Francesco
- The 2010 International Joint Conference on Neural Networks (IJCNN)
Parallel multi-value neural networks
patent, June 1998
- Sugaya, Fumiaki; Yatsuzuka, Youtaro
- US Patent Document 5,768,476
Central pattern generators for locomotion control in animals and robots: A review
journal, May 2008
- Ijspeert, Auke Jan
- Neural Networks, Vol. 21, Issue 4
Computational approaches to motor learning by imitation
journal, February 2003
- Schaal, Stefan; Ijspeert, Auke; Billard, Aude
- Philosophical Transactions of the Royal Society of London. Series B: Biological Sciences, Vol. 358, Issue 1431
Controlling multi-class error rates for MLP classifier by bias adjustment based on penalty matrix
conference, February 2012
- Pham, H. Trieu; Won, Yonggwan; Kim, Jungja
- Proceedings of the 6th International Conference on Ubiquitous Information Management and Communication
Sequence learning in a hierarchical temporal memory based system
patent, October 2012
- Jaros, Robert G.; George, Dileep; Hawkins, Jeffrey C.
- US Patent Document 8,285,667
Advances in applications of spiking neuron networks
conference, March 2000
- Cios, Krzysztof J.; Sala, Dorel M.
- SPIE Proceedings
A unified architecture for natural language processing: deep neural networks with multitask learning
conference, January 2008
- Collobert, Ronan; Weston, Jason
- Proceedings of the 25th international conference on Machine learning - ICML '08
Application of hebbian and anti-hebbian learning to nanotechnology-based physical neural networks
patent, August 2008
- Nugent, Alex
- US Patent Document 7,412,428
Systems and methods for reducing false positives produced by heuristics
patent, January 2014
- Kennedy, Mark
- US Patent Document 8,635,171
Understanding the interconnection network of SpiNNaker
conference, June 2009
- Navaridas, Javier; Luján, Mikel; Miguel-Alonso, Jose
- Proceedings of the 23rd international conference on Supercomputing
Multi-Modal Neural Network for Universal, Online Learning
patent-application, June 2017
- Modha, Dharmendra S.
- US Patent Application 15/456429; 20170185896
Event-Driven Universal Neural Network Circuit
patent-application, December 2015
- Modha, Dharmendra S.
- US Patent Application 13/594058; 20150371131
Learning apparatus, learning method, and program for efficiently learning dynamics
patent, May 2011
- Minamino, Katsuki; Ito, Masato; Kawamoto, Kenta
- US Patent Document 7,953,683
SpiNNaker: Mapping neural networks onto a massively-parallel chip multiprocessor
conference, June 2008
- Khan, M. M.; Lester, D. R.; Plana, L. A.
- 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)
Universal, Online Learning in Multi-Modal Perception-Action Semilattices
patent-application, September 2015
- Modha, Dharmendra S.
- US Patent Application 13/594045; 20150262056
Three-dimensional neural net for learning visuomotor coordination of a robot arm
journal, March 1990
- Martinetz, T. M.; Ritter, H. J.; Schulten, K. J.
- IEEE Transactions on Neural Networks, Vol. 1, Issue 1
Unsupervised training method for a neural net and a neural net classifier device
patent, November 1995
- Makram-Ebeid, Sherif
- US Patent Document 5,469,530
Multi-Modal Neural Network for Universal, Online Learning
patent-application, June 2013
- Modha, Dharmendra S.
- US Patent Application 13/596274; 20130159231
Unsupervised, Supervised and Reinforced Learning Via Spiking Computation
patent-application, September 2018
- Modha, Dharmendra S.
- US Patent Application 15/984167; 20180268294
Bidirectional recurrent neural networks
journal, January 1997
- Schuster, M.; Paliwal, K. K.
- IEEE Transactions on Signal Processing, Vol. 45, Issue 11
Multi-Context Configurable Memory Controller
patent-application, May 2012
- Rudosky, John M.; Wasson, Stephen L.; Box, Brian A.
- US Patent Application 13/216203; 20120131257
Scalable event-driven native parallel processing
conference, May 2010
- Rast, Alexander D.; Jin, Xin; Galluppi, Francesco
- Proceedings of the 7th ACM international conference on Computing frontiers
Method and neural network for speech recognition using a correlogram as input
patent, February 1998
- Tschirk, Wolfgang
- US Patent Document 5,721,807
Learning algorithms based on linearization
journal, January 1998
- Hahnloser, Richard
- Network: Computation in Neural Systems, Vol. 9, Issue 3
Co-training using RBF Nets and Different Feature Splits
conference, January 2006
- Feger, F.; Koprinska, I.
- The 2006 IEEE International Joint Conference on Neural Network Proceedings
Simultaneous order in nervous nets from a functional standpoint
journal, February 1984
- Koenderink, Jan J.
- Biological Cybernetics, Vol. 50, Issue 1
Unsupervised improvement of visual detectors using cotraining
conference, January 2003
- Levin,
- Proceedings Ninth IEEE International Conference on Computer Vision
Method and System for Invariant Pattern Recognition
patent-application, August 2015
- Jaros, Robert G.; Osindero, Simon Kayode
- US Patent Application 12/962632; 20150227849
Visualization and self organization of multidimensional data through equalized orthogonal mapping
patent, October 2000
- Pao, Yoh-Han; Meng, Zhuo
- US Patent Document 6,134,537
Method for implementing n-dimensional object recognition using dynamic adaptive recognition layers
patent, November 2011
- Bach, Klaus
- US Patent Document 8,059,890
Forming sparse representations by local anti-Hebbian learning
journal, December 1990
- Földiák, P.
- Biological Cybernetics, Vol. 64, Issue 2
Physical quantity analyzing method and apparatus thereof
patent, July 1997
- Ueda, Tomoaki; Sagane, Masayuki
- US Patent Document 5,646,868
Multi-modal neural network for universal, online learning
patent, January 2014
- Modha, Dharmendra S.
- US Patent Document 8,626,684
State-dependent computations: spatiotemporal processing in cortical networks
journal, January 2009
- Buonomano, Dean V.; Maass, Wolfgang
- Nature Reviews Neuroscience, Vol. 10, Issue 2
Spike transmission for neural networks
patent, January 1990
- Tomlinson, Jr., Max S.
- US Patent Document 4,893,255
Dimensional reduction for reward-based learning
journal, January 2006
- Swinehart, Christian D.; Abbott, L. F.
- Network: Computation in Neural Systems, Vol. 17, Issue 3
Computer intrusion detection system and method based on application monitoring
patent, February 2007
- Ghosh, Anup K.; Schatz, Michael; Michael, Christoph C.
- US Patent Document 7,181,768
Evolution of Neuro-Controllers for Robots' Alignment using Local Communication
journal, January 2009
- Gutiérrez, Álvaro; Tuci, Elio; Campo, Alexandre
- International Journal of Advanced Robotic Systems, Vol. 6, Issue 1
Learning method for multi-level neural network
patent, June 1998
- Yatsuzuka, Youtaro
- US Patent Document 5,764,860
Unsupervised, Supervised and Reinforced Learning Via Spiking Computation
patent-application, January 2017
- Modha, Dharmendra S.
- US Patent Application 14/945316; 20170017878
Application of neural networks as an aid in medical diagnosis and general anomaly detection
patent, July 1994
- Stafford, Richard G.; Mickewich, Daniel J.; Beutel, Jacob
- US Patent Document 5,331,550
Fast and Robust Learning by Reinforcement Signals: Explorations in the Insect Brain
journal, August 2009
- Huerta, Ramón; Nowotny, Thomas
- Neural Computation, Vol. 21, Issue 8
Unsupervised, Supervised, and Reinforced Learning Via Spiking Computation
patent-application, December 2015
- Modha, Dharmendra S.
- US Patent Application 14/494372; 20150363690
Hierarchically-Scalable Reconfigurable Integrated Circuit Architecture with Unit Delay Modules
patent-application, May 2012
- Wasson, Stephen L.; Box, Brian A.; Rudosky, John M.
- US Patent Application 13/216182; 20120126850
Information processing apparatus, information processing method, pattern recognition apparatus, and pattern recognition method
patent, March 2010
- Matsugu, Masakazu; Mori, Katsuhiko; Ishii, Mie
- US Patent Document 7,676,441
Data-Driven Integrated Circuit Architecture
patent-application, May 2012
- Kelen, Steven Hennick; Box, Brian A.; Rudosky, John M.
- US Patent Application 13/216193; 20120126851
Reconfigurable Integrated Circuit Architecture with On-Chip Configuration and Reconfiguration
patent-application, May 2012
- Box, Brian A.; Rudosky, John M.; Wasson, Stephen L.
- US Patent Application 13/216212; 20120131288
Unsupervised, Supervised, and Reinforced Learning Via Spiking Computation
patent-application, March 2013
- Modha, Dharmendra S.
- US Patent Application 13/235342; 20130073493
Solving the distal reward problem through linkage of STDP and dopamine signaling
patent, January 2012
- Izhikevich, Eugene
- US Patent Document 8,103,602
Cognitive Architecture for Learning, Action, and Perception
patent-application, April 2008
- Srinivasa, Narayan; Khosia, Deepak
- US Patent Application 11/801377; 20080091628
Event-Driven Universal Neural Network Circuit
patent-application, March 2013
- Modha, Dharmendra S.
- US Patent Application 13/235343; 20130073494
Universal, Online Learning in Multi-Modal Perception-Action Semilattices
patent-application, January 2014
- Modha, Dharmendra S.
- US Patent Application 13/325316; 20140019393
Methods and Apparatus for Transmitting Signals Through Network Elements for Classification
patent-application, March 2008
- Cecchi, Guillermo Alberto; Kozloski, James Robert; Peck, III, Charles Clyde
- US Patent Application 11/847639; 20080071712
Optimizing Workflow Engines
patent-application, December 2012
- Saha, Dhrubajyoti; Sarangi, Smruti Ranjan
- US Patent Application 13/584314; 20120311595
Electronic Synapses for Reinforcement Learning
patent-application, October 2014
- Chang, Leland; Modha, Dharmendra S.; Montoye, Robert K.
- US Patent Application 12/982505; 20140310220
Unsupervised, Supervised and Reinforced Learning Via Spiking Computation
patent-application, September 2014
- Modha, Dharmendra S.
- US Patent Application 13/587424; 20140250039
An FPGA platform for on-line topology exploration of spiking neural networks
journal, June 2005
- Upegui, Andres; Peña-Reyes, Carlos Andrés; Sanchez, Eduardo
- Microprocessors and Microsystems, Vol. 29, Issue 5