Patent
1993-07-29
1996-01-16
MacDonald, Allen R.
395 24, 395 23, G06F 1518
Patent
active
054855489
ABSTRACT:
In a neural network configured of neuron model cells, each neuron model cell is adapted to hold an input signal when a forward process is performed and to hold an error signal inputted when a learning process is performed. The signal processing apparatus is arranged to execute the forward process and the learning process in parallel.
REFERENCES:
patent: 4518866 (1985-05-01), Clymer
patent: 4737929 (1988-04-01), Denker
patent: 4918618 (1990-04-01), Tomlinson
patent: 5119468 (1992-06-01), Owens
A Neural Net Embedded Processor with a Dynamically Reconfigurable Pipeline Architecture, T. Satonaka, IEEE/4-6 Jun. 1992.
A Digital "Snake" Implementation of the Back-Propagation Neural Net F. Piazza IEEE/8-11 May 1989.
A Comparison of Processor Topologies for a Fast Trainable Neural Net for Speech Recognition. Y. Suzukie, IEEE 23-26 May 1989.
Hashimoto Atsuo
Oteki Sugitaka
Dorvil Richemond
MacDonald Allen R.
Ricoh & Company, Ltd.
LandOfFree
Signal processing apparatus using a hierarchical neural network does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Signal processing apparatus using a hierarchical neural network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Signal processing apparatus using a hierarchical neural network will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-315660