Neural cortex

Data processing: artificial intelligence – Neural network – Learning task

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

Reexamination Certificate

active

10398279

ABSTRACT:
A neural network system includes a random access memory (RAM); and an index-based weightless neural network with a columnar topography; wherein patterns of binary connections and values of output nodes' activities are stored in the RAM. Information is processed by pattern recognition using the neural network by storing a plurality of output patterns to be recognized in a pattern index; accepting an input pattern and dividing the input pattern into a plurality of components; and processing each component according to the pattern index to identify a recognized output pattern corresponding to the input pattern.

REFERENCES:
patent: 5285522 (1994-02-01), Mueller
patent: 5621848 (1997-04-01), Wang
patent: 5893058 (1999-04-01), Kosaka
patent: 5995868 (1999-11-01), Dorfmeister et al.
patent: 6058206 (2000-05-01), Kortge
patent: 6094647 (2000-07-01), Kato et al.
patent: 6393413 (2002-05-01), Jorgensen et al.
patent: 6549804 (2003-04-01), Osorio et al.
patent: 2002/0095617 (2002-07-01), Norman
patent: 0 684 576 (1995-11-01), None
patent: 0 709 801 (1996-05-01), None
Associative dynamics in chaotic neural networks Ikeguchi, T.; Aihara, K.; Neural Networks, 1991. 1991 IEEE International Joint Conference on Nov. 18-21, 1991 pp. 2282-2287 vol. 3 Digital Object Identifier 10.1109/IJCNN.1991.170728.
Design and analysis of a nonequilibrium cross-coupled network with a detectable similarity measure Shimono, M.; Yamakawa, T.; Neural Networks, IEEE Transactions on vol. 11, Issue 1, Jan. 2000 pp. 57-68 Digital Object Identifier 10.1109/72.822510.
Optical inner-product implementations for multi-layer BAM with 2-dimensional patterns Hyuek-Jae Lee; Soo-Young Lee; Cheol Hoon Park; Sang Yung Shin; Neural Networks, 1991. 1991 IEEE International Joint Conference on Nov. 18-21, 1991 pp. 1729-1734 vol. 2 Digital Object Identifier 10.1109/IJCNN.1991.170675.
On reducing the influence of noise in a new model for optimal linear associative memory Tuan, C.-H.; Li, B.; Yau, S.-T.; Mullin, L.; Neural Networks, 1991. 1991 IEEE International Joint Conference on Nov. 18-21, 1991 pp. 2764-2769 vol. 3 Digital Object Identifier 10.1109/IJCNN.1991.170333.
Ho et al., “A Computational Model for Recognition of Multifont Word Images,” Machine Vision and Applications (1992), pp. 5:157-168.
Kan et al., “A Probabilistic Logic Neuron Network for Associative Learning,” IEEE First International Conference of Neural Networks (Jun. 21-24, 1987), The Institute of Electrical and Electronics Engineers, Inc., San Diego, California, pp. II-541-II-548.
Aleksander et al., “Computer Vision Systems for Industry: Comparisons”, Digital Systems for Industrial Automation, 1982, pp. 179, 183-193.
Bledsoe et al., “Pattern Recognition and Reading by Machine”, Proceedings of the Eastern Joint Computer Conference, 1959 pp. 225-232.
Cook, Normal D., “The Brain Code”, 1986, p. 96, Methuen & Co., Ltd.
Kanerva, P., “Sparse Distributed Memory”, date unknown, pp. 56, 72, 73, Cambridge, MA: NIT Press.
Morciniec et al., “The n-Tuple Classifier: Too Good to Ignore”, 1995, pp. 1-11.
Schalkoff, Robert J., “Artificial Neural Networks”, 1997, pp. 2,10,390,391,399, The McGraw-Hill Companies, Inc.
International Search Report dated Apr. 20, 2001, 3 pages.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Neural cortex does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Neural cortex, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural cortex will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-3878349

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.