Long-term memory neural network modeling memory-chaining...

Data processing: artificial intelligence – Neural network – Learning task

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C706S027000

Reexamination Certificate

active

07747549

ABSTRACT:
A STM network11for temporarily storing input pattern vectors is formed in Phases 1 and 2, and then layered LTM networks2to L are formed successively by assigning output vectors provided by the STM network11as input vectors. In phase 4, a LTM network1for intuitive outputs to which input pattern vectors are applied directly is formed by taking the parameters of comparatively highly activated centroids among centroids in the LTM networks2to L. In phase 5, the parameters of the comparatively highly activated centroids among the centroids in the LTM networks2to L are fed back as the parameters of the centroids in the STM network. In phase 3, the LTM networks2to L are reconstructed at a particular time or in a fixed period by giving the centroid vectors of the LTM networks2to L again as input pattern vectors to the STM network11.

REFERENCES:
patent: 5335291 (1994-08-01), Kramer et al.
patent: 5418886 (1995-05-01), Oita et al.
patent: 5659666 (1997-08-01), Thaler
patent: 5920852 (1999-07-01), Graupe
patent: 5995644 (1999-11-01), Lai et al.
patent: 6175772 (2001-01-01), Kamiya et al.
patent: 6219657 (2001-04-01), Hatayama
patent: 6249780 (2001-06-01), Mizokawa
patent: 6347310 (2002-02-01), Passera
patent: 6446056 (2002-09-01), Sadakuni
patent: 06-052141 (1994-02-01), None
Wacquant et al. (Wacquant), Inward Relearning: A Step Towards Long-Term Memory, 1996.
Chambers et al., “Heuristic Pattern Correction Scheme Using Adaptively Trained Generalized Regression Neural Networks”, 2001.
Donald F. Specht; IEEE Transactions of Neural Networks, vol. 2, No. 6, Nov. 1991, pp. 568-576.
Tetsuya Hoya et al.; IEEE Transactions of Neural Networks, vol. 12, No. 1, Jan. 2001, pp. 91-100.
Donald F. Specht; Neural Networks, vol. 3, pp. 109-118, 1990, pp. 109-118.
Hoshino, et al.; “On Multilayer RBF Networks and a Novel Pyramid Network”; pp. 31-37.

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

Long-term memory neural network modeling memory-chaining... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Long-term memory neural network modeling memory-chaining..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Long-term memory neural network modeling memory-chaining... will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-4240611

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