Data processing: artificial intelligence – Machine learning
Reexamination Certificate
2011-07-19
2011-07-19
Holmes, Michael (Department: 2129)
Data processing: artificial intelligence
Machine learning
Reexamination Certificate
active
07983998
ABSTRACT:
A Hierarchical Temporal Memory (HTM) network has at least first nodes and a second node at a higher level than the first nodes. The second node provides an inter-node feedback signal to the first nodes for grouping patterns and sequences (or co-occurrences) in input data received at the first nodes at the first nodes. The second node collects forward signals from the first nodes; and thus, the second node has information about the grouping of the patterns and sequences (or co-occurrences) at the first nodes. The second node provides inter-node feedback signals to the first nodes based on which the first nodes may perform the grouping of the patterns and sequences (or co-occurrences) at the first nodes. Also, a node in a Hierarchical Temporal Memory (HTM) network comprising a co-occurrence detector and a group learner coupled to the co-occurrence detector. The group learner provides an intra-node feedback signal to the co-occurrence detector including information on the grouping of the co-occurrences. The co-occurrence detector may select co-occurrences to be split, merged, retained or discarded based on the intra-node feedback signals.
REFERENCES:
patent: 4766534 (1988-08-01), DeBenedictis
patent: 4845744 (1989-07-01), DeBenedictis
patent: 5255348 (1993-10-01), Nenov
patent: 5712953 (1998-01-01), Langs
patent: 6122014 (2000-09-01), Panusopone et al.
patent: 6195622 (2001-02-01), Altschuler et al.
patent: 6400996 (2002-06-01), Hoffberg et al.
patent: 6468069 (2002-10-01), Lemelson et al.
patent: 6567814 (2003-05-01), Bankier et al.
patent: 6625585 (2003-09-01), MacCuish et al.
patent: 6714941 (2004-03-01), Lerman et al.
patent: 6751343 (2004-06-01), Ferrell et al.
patent: 6957241 (2005-10-01), George
patent: 7088693 (2006-08-01), George
patent: 7251637 (2007-07-01), Caid et al.
patent: 7613675 (2009-11-01), Hawkins et al.
patent: 7620608 (2009-11-01), Jaros et al.
patent: 7624085 (2009-11-01), Hawkins et al.
patent: 7739208 (2010-06-01), George et al.
patent: 7826990 (2010-11-01), Nasle et al.
patent: 7840395 (2010-11-01), Nasle et al.
patent: 7840396 (2010-11-01), Radibratovic et al.
patent: 7844439 (2010-11-01), Nasle et al.
patent: 7844440 (2010-11-01), Nasle et al.
patent: 2002/0150044 (2002-10-01), Wu et al.
patent: 2003/0069002 (2003-04-01), Hunter et al.
patent: 2003/0123732 (2003-07-01), Miyazaki et al.
patent: 2003/0167111 (2003-09-01), Kipersztok et al.
patent: 2004/0002838 (2004-01-01), Oliver et al.
patent: 2004/0148520 (2004-07-01), Talpade et al.
patent: 2004/0267395 (2004-12-01), Discenzo et al.
patent: 2005/0063565 (2005-03-01), Nagaoka et al.
patent: 2005/0190990 (2005-09-01), Burt et al.
patent: 2005/0222811 (2005-10-01), Jakobson et al.
patent: 2006/0184462 (2006-08-01), Hawkins
patent: 2006/0212444 (2006-09-01), Handman et al.
patent: 2006/0235320 (2006-10-01), Tan et al.
patent: 2006/0248026 (2006-11-01), Aoyama et al.
patent: 2006/0248073 (2006-11-01), Jones et al.
patent: 2006/0253491 (2006-11-01), Gokturk et al.
patent: 2006/0259163 (2006-11-01), Hsiung et al.
patent: 2007/0005531 (2007-01-01), George et al.
patent: 2007/0192264 (2007-08-01), Hawkins et al.
patent: 2007/0192267 (2007-08-01), Hawkins et al.
patent: 2007/0192268 (2007-08-01), Hawkins et al.
patent: 2007/0192269 (2007-08-01), Saphir et al.
patent: 2007/0192270 (2007-08-01), Hawkins et al.
patent: 2007/0228703 (2007-10-01), Breed
patent: 2007/0276774 (2007-11-01), Ahmad et al.
patent: 2008/0059389 (2008-03-01), Jaros et al.
patent: 2009/0006289 (2009-01-01), Jaros et al.
patent: 2010/0207754 (2010-08-01), Shostak et al.
patent: 1557990 (2005-07-01), None
patent: WO 2006/063291 (2006-06-01), None
patent: WO 2008/067326 (2008-06-01), None
patent: WO 2009/006231 (2009-01-01), None
Unsupervised Hebbian learning by recurrent multilayer neural networks for temporal hierarchical pattern recognition, Lo, J.T.-H.; Information Sciences and Systems (CISS), 2010 44th Annual Conference on Digital Object Identifier: 10.1109/CISS.2010.5464925 Publication Year: 2010 , pp. 1-6.
Online temporal pattern learning, Farahmand, N.; Dezfoulian, M.H.; GhiasiRad, H.; Mokhtari, A.; Nouri, A.; Neural Networks, 2009. IJCNN 2009. International Joint Conference on Digital Object Identifier: 10.1109/IJCNN.2009.5178844 Publication Year: 2009 , pp. 797-802.
Spatio—Temporal Memories for Machine Learning: A Long-Term Memory Organization, Starzyk, J.A.; He, H.; Neural Networks, IEEE Transactions on vol. 20 , Issue: 5 Digital Object Identifier: 10.1109/TNN.2009.2012854 Publication Year: 2009 , pp. 768-780.
A neural network model of spatio-temporal pattern recognition, recall, and timing, Mannes, C.; Neural Networks, 1992. IJCNN., International Joint Conference on vol. 4 Digital Object Identifier: 10.1109/IJCNN.1992.227281 Publication Year: 1992 , pp. 109-114 vol. 4.
European Patent Office Communication, European Patent Application No. 07750385.2, Dec. 6, 2010, eight pages.
European Patent Office Examination Report, European Patent Application No. 08796030.8, Dec. 6, 2010, seven pages.
Lim, K. et al., “Estimation of Occlusion and Dense Motion Fields in a Bidirectional Bayesian Framework,”IEEE Transactions on Pattern Analysis and Machine Intelligence, May 2002, pp. 712-718, vol. 24, No. 5.
United States Office Action, U.S. Appl. No. 11/680,197, Sep. 14, 2010, seventeen pages.
Dimitrova, N. et al., “Motion Recovery for Video Content Classification,” ACM Transactions on Information Systems, Oct. 1995, pp. 408-439, vol. 13, No. 4.
Dolin, R. et al., “Scalable Collection Summarization and Selection,” Association for Computing Machinery, 1999, pp. 49-58.
Guerrier, P., “A Generic Architecture for On-Chip Packet-Switched Interconnections,” Association for Computing Machinery, 2000, pp. 250-256.
Kim, J. et al., “Hierarchical Distributed Genetic Algorithms: A Fuzzy Logic Controller Design Application,” IEEE Expert, Jun. 1996, pp. 76-84.
Mishkin, M. et al., “Hierarchical Organization of Cognitive Memory,” Phil. Trans. R. Soc. B., 1997, pp. 1461-1467, London.
Park, S. et al., “Recognition of Two-person Interactions Using a Hierarchical Bayesian Network,” ACM SIGMM International Workshop on Video Surveillance (IWVS) 2003, pp. 65-76, Berkeley, USA.
Poppel, E., “A Hierarchical Model of Temporal Perception,” Trends in Cognitive Sciences, May 1997, pp. 56-61, vol. 1, No. 2.
Tsinarakis, G.J. et al. “Modular Petri Net Based Modeling, Analysis and Synthesis of Dedicated Production Systems,” Proceedings of the 2003 IEEE International Conference on Robotics and Automation, Sep. 14-19, 2003, pp. 3559-3564, Taipei, Taiwan.
Tsinarakis, G.J. et al. “Modular Petri Net Based Modeling, Analysis, Synthesis and Performance Evaluation of Random Topology Dedicated Production Systems,” Journal of Intelligent Manufacturing, 2005, vol. 16, pp. 67-92.
United States Office Action, U.S. Appl. No. 11/680,197, Mar. 23, 2010, 12 pages.
United States Office Action, U.S. Appl. No. 11/713,157, Mar. 31, 2010, 14 pages.
United States Office Action, U.S. Appl. No. 11/622,458, Apr. 1, 2010, 16 pages.
United States Office Action, U.S. Appl. No. 11/622,455, Apr. 21, 2010, 12 pages.
Wu, G. et al., “Multi-camera Spatio-temporal Fusion and Biased Sequence-data Learning for Security Surveillance,” Association for Computing Machinery, 2003, pp. 528-538.
Archive of “Numenta Platform for Intelligent Computing Programmer's Guide,” Numenta, Mar. 7, 2007, pp. 1-186, www.numenta.com, [Online] Archived by http://archive.org on Mar. 19, 2007; Retrieved on Aug. 13, 2008 Retrieved from the Internet<URL:http://web.archive.org/web/20070319232606/http://www.numenta.com/for-developers/software/pdf
upic—prog—guide.pdf>.
Csapo, A.B. et al., “Object Categorization Using VFA-Generated Nodemaps and Hierarchical Temporal Memories,” IEEE International Conference on Computational Cybernetics, IEEE, Oct. 7, 2007, pp. 257-262.
Ding, C.H.Q., “Cluster Merging and Splitting in Hierarchical Clus
George Dileep
Jaros Robert G.
Fenwick & West LLP
Holmes Michael
Numenta, Inc.
LandOfFree
Feedback in group based hierarchical temporal memory system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Feedback in group based hierarchical temporal memory system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Feedback in group based hierarchical temporal memory system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2625466