US4945494A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Neural network and system
Assignee: Texas Instruments Inc
•
Filing: 1989-06-16
•
Granted: 1990-07-31
•
Expires: 2009-06-16
Abstract
Abstract Neural network systems (100) with learning and recall are applied to clustered multiple-featured data (122, 124, 126) and analog data.
Inventors
- 👤 Perry A. Penz
- 👤 Michael T. Gately
- 👤 Alan J. Katz
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-25 14:06
CPC Classifications
G; G01; G01S; G01S7/00; G01S7/02; G01S7/28; G01S7/285; G01S7/292; G01S7/41; G01S7/417; G06; G06F; G06F18/00; G06F18/20; G06F18/21; G06F18/213; G06F18/2135; G06N; G06N3/00; G06N3/02; G06N3/04; G06N3/044; G06N3/045; G06N3/0455; G06N3/08; G06N3/09
Claims Analysis
Total Claims: 11
Claim 1
Independent Claim
76 words
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.
Claim 2
Dependent Claim
76 words
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.
Claim 3
Dependent Claim
51 words
The processor of claim 1, further comprising: (a) a classifying neural network having stored information in a format of vectors recalled from said clustering network using said recall rule, said classifying network comparing said stored information recalled from said clustering network with other information stored therein with a second recall rule.
Claim 4
Dependent Claim
82 words
The processor of claim 1, further comprising: (a) a tracker receiving the output of said encoder and recalled vectors from said neural network and forming cluster vectors in response thereto with correspondence information from said recalled vectors to prohibit recall of the portion of said output of said encoder corresponding to a previously formed one of said cluster vectors; and (b) a classifier having stored information therein providing an output indicative of the correspondence between said stored information and said cluster vectors.
Claim 5
Dependent Claim
24 words
The processor of claim 1, wherein: (a) said learning rule is a Widrow-Hoff learning; and (b) said recall rule is a BSB-type recall rule.
Claim 6
Independent Claim
72 words
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.
Claim 7
Independent Claim
72 words
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.
Claim 8
Dependent Claim
19 words
The method of claim 5, wherein; (a) said stored information is stored in a second thresholded analog neural network.
Claim 9
Dependent Claim
31 words
The method of claim 5, comprising the further steps of: (a) deleting a portion of each of said recalled versions; and (b) adding further information to each of said recalled versions.
Claim 10
Independent Claim
52 words
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.
Claim 11
Independent Claim
52 words
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.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1993-07-30 | 1994-01-29 | 1994-07-31 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1997-07-30 | 1998-01-29 | 1998-07-31 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2001-07-30 | 2002-01-29 | 2002-07-31 | $7700.00 | Window Closed / Lapsed |