Patent US5416850A successfully refreshed from Google Patents.
US5416850A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Associative pattern conversion system and adaption method thereof
Assignee: Ezel Inc
•
Filing: 1993-03-18
•
Granted: 1995-05-16
•
Expires: 2013-03-18
Abstract
Abstract An associative pattern conversion system is disclosed which may be used for image recognition. The system includes an image input portion, an image processing portion and a recognition portion. The image processing portion includes a process unit for extracting characteristics and a frame memory for holding image data. The recognition portion, which includes a component for the learning of data to be associated, obtains the extracted characteristics from the image processing portion and performs associative pattern conversion from the image input portion. The system of the present invention may be applied to any neural network, preferably a matrix calculation type neural network.
Inventors
- 👤 Sunao Takatori
- 👤 Ryohei Kumagai
- 👤 Makoto Yamamoto
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-08 14:37
CPC Classifications
G; G06; G06N; G06N3/00; G06N3/02; G06N3/06; G06N3/063; G06V; G06V30/00; G06V30/10; G06V30/19; G06V30/192; G06V30/194
Claims Analysis
Total Claims: 6
Claim 1
Independent Claim
153 words
An associative pattern conversion system for allowing recognition of an input signal, said conversion system comprising: generating means for sensing a first object and for generating input data which is representative of selected characteristics of said sensed first object; a memory for storing at least said input data, weight data, output data nd reference data; weight variable determining means for evaluating a relationship between said input data, said output data and said reference data stored in said memory and determining the value of a weight variable based on said relationship so as to decrease said weight variable over time in such a manner that said weight variable never increases; weight changing means for changing said weight data, which is stored in said memory, in accordance with said weight variable; and recognition means for receiving said input signal, and for outputting, based upon said input signal and said weight data, an associated recognition signal.
Claim 2
Dependent Claim
153 words
An associative pattern conversion system for allowing recognition of an input signal, said conversion system comprising: generating means for sensing a first object and for generating input data which is representative of selected characteristics of said sensed first object; a memory for storing at least said input data, weight data, output data nd reference data; weight variable determining means for evaluating a relationship between said input data, said output data and said reference data stored in said memory and determining the value of a weight variable based on said relationship so as to decrease said weight variable over time in such a manner that said weight variable never increases; weight changing means for changing said weight data, which is stored in said memory, in accordance with said weight variable; and recognition means for receiving said input signal, and for outputting, based upon said input signal and said weight data, an associated recognition signal.
Claim 3
Dependent Claim
23 words
An associative pattern conversion system according to claim 1, wherein said weight variable determining means multiplies said output data by said input data.
Claim 4
Dependent Claim
51 words
An associative pattern conversion system according to claim 1, further comprising: means for multiplying each of said input data with a corresponding one of said weight data, means for integrating said multiplication results, and means for generating an output data according to a difference between said integration result and a threshold.
Claim 5
Dependent Claim
27 words
An associative pattern conversion system according to claim 3, wherein said difference between said integration result and said threshold is determined by a table of predetermined values.
Claim 6
Dependent Claim
14 words
An associative pattern conversion system according to claim 4, wherein said table is rewritable.
References Cited (Backward Citations)
US3218475A
Cited
US3209328A
Cited
US3310783A
Cited
US3310784A
Cited
US3325787A
Cited
US3408627A
Cited
US3435422A
Cited
US3602888A
Cited
US3601811A
Cited
US3638196A
Cited
US4326259A
Cited
US4660166A
Cited
US4760604A
Cited
US4730295A
Cited
US4803736A
Cited
US4805225A
Cited
US4783830A
Cited
US4887306A
Cited
US5040230A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1998-05-15 | 1998-11-14 | 1999-05-16 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2002-05-15 | 2002-11-14 | 2003-05-16 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2006-05-15 | 2006-11-14 | 2007-05-16 | $7700.00 | Window Closed / Lapsed |