Data processing: artificial intelligence – Neural network – Structure
Reexamination Certificate
2007-08-07
2007-08-07
Hirl, Joseph P (Department: 2129)
Data processing: artificial intelligence
Neural network
Structure
C706S042000, C706S018000, C706S025000, C706S026000, C706S027000
Reexamination Certificate
active
10137969
ABSTRACT:
An improved Artificial Neural Network (ANN) is disclosed that comprises a conventional ANN, a database block, and a compare and update circuit. The conventional ANN is formed by a plurality of neurons, each neuron having a prototype memory dedicated to store a prototype and a distance evaluator to evaluate the distance between the input pattern presented to the ANN and the prototype stored therein. The database block has: all the prototypes arranged in slices, each slice being capable to store up to a maximum number of prototypes; the input patterns or queries to be presented to the ANN; and the distances resulting of the evaluation performed during the recognition/classification phase. The compare and update circuit compares the distance with the distance previously found for the same input pattern updates or not the distance previously stored.
REFERENCES:
patent: 5649070 (1997-07-01), Connell et al.
patent: 2002/0194159 (2002-12-01), Kamath et al.
patent: 2003/0018598 (2003-01-01), Cawse et al.
Robert David, Erin Williams, Ghislain de Tremiolles, “Description and Practical Uses of IBM ZISC036”, Ninth Workshop on Virtual Intelligence/Dynamic Neural Networks, Stockholm, Sweeden, Jun. 15, 1998.
Thomas Plum, “Reliable Data Structures in C” ISBN 0-911537-04-X, copyright 1985. Chapter 3, p. 7.
‘Reliable Data Structures in C’:Thomas Plum, 1985, Noble Book Press, chapter 3, p. 7.(3-7).
SPIE Digital Library, http://spiedl.aip.org/bdt.jsp?KEY=PSISDG&Volume=3728&Issue=1&bpoc=volrange&scode=3700+-+3799, p. 1 & 4.
‘Reliable data structures in C’, Thomas Plum, 1985, Noble Book Press, 3-7.
‘Description and practical uses of IBM ZISC036’: David, 1999, SPIE, vol. 3728, 0277-786X/99, 198-211.
De Tremiolles Ghislain Imbert
Tannhof Pascal
Coughlan Peter
Hirl Joseph P
LandOfFree
Method and circuits to virtually increase the number of... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and circuits to virtually increase the number of..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and circuits to virtually increase the number of... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3898887