Neural network and system
First Claim
Patent Images
1. An information processor, comprising:
- (a) an encoder, said encoder encoding input information at least partially into a position type code format; and
(b) a clustering neural network providing an output therefrom, said clustering network having an input receiving said output of said encoder and said output of said clustering network, said clustering neural network clustering said input thereto with thresholded analog neurons in conjunction with a learning rule and a recall rule to preserve analog aspects.
1 Assignment
0 Petitions
Accused Products
Abstract
Neural network systems (100) with learning and recall are applied to clustered multiple-featured data (122, 124, 126) and analog data.
-
Citations
8 Claims
-
1. An information processor, comprising:
-
(a) an encoder, said encoder encoding input information at least partially into a position type code format; and (b) a clustering neural network providing an output therefrom, said clustering network having an input receiving said output of said encoder and said output of said clustering network, said clustering neural network clustering said input thereto with thresholded analog neurons in conjunction with a learning rule and a recall rule to preserve analog aspects. - View Dependent Claims (2, 3, 4)
-
-
5. A method of information processing, comprising the steps of:
-
(a) encoding said information into thermometer code format; (b) learning said encoded information with a thresholded analog neural network; (c) recalling at least some of said information from said neural network; (d) recoding said recalled information; (e) comparing said encoded information with said recoded recalled information with noncomparable encoded leading to further recall; and (f) comparing said recoded recalled information with stored information. - View Dependent Claims (6, 7)
-
-
8. A method of processing multiple-feature information, comprising the steps of:
-
(a) encoding information by concatenated thermometer codes of features of said information; (b) learning without saturation said encoded information in a thresholded analog neural network; and (c) inputting said encoded information into said network and recalling processed versions of said encoded information.
-
Specification