Patent US4995088A successfully refreshed from Google Patents.
US4995088A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Super resolution
Assignee: TRUSTEES OF UNIVERSITY OF PA A NON-PROFIT CORP OF
•
Filing: 1989-11-22
•
Granted: 1991-02-19
•
Expires: 2009-11-22
Abstract
Abstract Data analysis systems are provided, especially target imaging and identification systems, which utilize a CAM that associatively stores a plurality of known data sets such as target data sets in a synaptic interconnectivity matrix modeled upon the model of learning of neural networks. In accordance with preferred embodiments the systems are able to identify unknown objects when only a partial data set from the object is available. The system is robust and fast, utilizing parallel processing due to the massive interconnectivity of neural elements so that the image produced exhibits the properties of super-resolution. Since the system is modeled after a neural network, it is fault tolerant and highly reliable.
Inventors
- 👤 Nabil Farhat
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-23 15:11
CPC Classifications
G; G01; G01S; G01S7/00; G01S7/02; G01S7/41; G01S7/417; G06; G06N; G06N3/00; G06N3/02; G06N3/06; G06N3/067; G06N3/0675; G06V; G06V30/00; G06V30/10; G06V30/19; G06V30/192; G06V30/194
Claims Analysis
Total Claims: 63
Claim 1
Independent Claim
126 words
A data analysis system comprising: a first array for receiving input data comprising a plurality of neural elements for transmitting data signals; a memory matrix for processing the data signals transmitted by the elements of the first array, said memory matrix having associatively stored therein in accordance with a Hebbian model of learning for neural networks, at least one quantized feature space classifier of a known data set; a second array having a plurality of neural elements for receiving the data signals processed by the memory matrix; the neural elements of the second array being operatively coupled in feedback with the neural elements of the first array wherein the neural elements of the second array provide feedback input for the neural elements of the first array.
Claim 2
Dependent Claim
126 words
A data analysis system comprising: a first array for receiving input data comprising a plurality of neural elements for transmitting data signals; a memory matrix for processing the data signals transmitted by the elements of the first array, said memory matrix having associatively stored therein in accordance with a Hebbian model of learning for neural networks, at least one quantized feature space classifier of a known data set; a second array having a plurality of neural elements for receiving the data signals processed by the memory matrix; the neural elements of the second array being operatively coupled in feedback with the neural elements of the first array wherein the neural elements of the second array provide feedback input for the neural elements of the first array.
Claim 3
Dependent Claim
17 words
The system of claim 1, wherein the neural elements of the first array comprise light emitting elements.
Claim 4
Dependent Claim
15 words
The system of claim 1, wherein the neural elements of the second array comprise photo-detectors.
Claim 5
Dependent Claim
10 words
The system of claim 1, wherein the feedback is electronic.
Claim 6
Dependent Claim
19 words
The system of claim 1, wherein the neural elements of the first and second arrays are optical bistability devices.
Claim 7
Dependent Claim
11 words
The system according to claim 1, wherein the feedback is optical.
Claim 8
Dependent Claim
18 words
The system of claim 1, wherein the feature space classifier of the known data set is stored auto-associatively.
Claim 9
Dependent Claim
18 words
The system of claim 1, wherein the feature space classifier of the known data set is stored hetero-associatively.
Claim 10
Dependent Claim
19 words
The system of claim 1, wherein the feature space classifier of the known data set is stored cyclic hetero-associatively.
Claim 11
Dependent Claim
25 words
The system of claim 1, further comprising means for gathering electromagnetic scattering data for construction of the feature space classifier of a known data set.
Claim 12
Dependent Claim
25 words
The system of claim 1, further comprising means for gathering acoustical scattering data for construction of the feature space classifier of a known data set.
Claim 13
Dependent Claim
19 words
The system of claim 1, further comprising means for gathering electromagnetic scattering data for input to the first array.
Claim 14
Dependent Claim
19 words
The system of claim 1, further comprising means for gathering acoustical scattering data for input to the first array.
Claim 15
Dependent Claim
13 words
The system of claim 1, wherein the feedback input reaches steady state auto-associatively.
Claim 16
Dependent Claim
13 words
The system of claim 1, wherein the feedback input reaches steady state hetero-associatively.
Claim 17
Dependent Claim
14 words
The system of claim 1, wherein the feedback input reaches steady state cyclic hetero-associatively.
Claim 18
Dependent Claim
11 words
The system of claim 1, wherein the memory matrix is synaptic.
Claim 19
Dependent Claim
11 words
The system of claim 1, wherein the memory matrix is interconnected.
Claim 20
Dependent Claim
14 words
The system of claim 1, wherein the feature space classifier is a sinogram classifier.
Claim 21
Dependent Claim
136 words
A data analysis system comprising: a first array for receiving input data comprising a plurality of optical neural elements for transmitting optical data signals; a memory matrix for optically processing the optical data signals transmitted by the optical neural elements of the first array, said memory matrix having associatively stored therein in accordance with a Hebbian model of learning for neural networks, at least one quantized feature space classifier of a known data set; a second array comprising a plurality of optical neural elements for receiving the optical data signals processed by the memory matrix; the optical neural elements of the second array being operatively coupled in feedback with the optical neural elements of the first array whereby the neural elements of the second array provide feedback input for the neural elements of the first array.
Claim 22
Dependent Claim
136 words
A data analysis system comprising: a first array for receiving input data comprising a plurality of optical neural elements for transmitting optical data signals; a memory matrix for optically processing the optical data signals transmitted by the optical neural elements of the first array, said memory matrix having associatively stored therein in accordance with a Hebbian model of learning for neural networks, at least one quantized feature space classifier of a known data set; a second array comprising a plurality of optical neural elements for receiving the optical data signals processed by the memory matrix; the optical neural elements of the second array being operatively coupled in feedback with the optical neural elements of the first array whereby the neural elements of the second array provide feedback input for the neural elements of the first array.
Claim 23
Dependent Claim
18 words
The system of claim 20, wherein the optical neural elements of the first array comprise light emitting elements.
Claim 24
Dependent Claim
15 words
The system of claim 20, wherein the neural elements of the second array are photo-detectors.
Claim 25
Dependent Claim
10 words
The system of claim 20, wherein the feedback is electronic.
Claim 26
Dependent Claim
10 words
The system of claim 20, wherein the feedback is optical.
Claim 27
Dependent Claim
19 words
The system of claim 20, wherein the neural elements of the first and second arrays are optical bistability devices.
Claim 28
Dependent Claim
16 words
The system of claim 20, wherein the sinogram classifier of the data set is stored auto-associatively.
Claim 29
Dependent Claim
17 words
The system of claim 20, wherein the sinogram classifier of the known data set is stored hetero-associatively.
Claim 30
Dependent Claim
18 words
The system of claim 20, wherein the sinogram classifier of the known data set is stored cyclic hetero-associatively.
Claim 31
Dependent Claim
25 words
The system of claim 20, further comprising means for gathering electromagnetic scattering data for construction of the feature space classifier of a known data set.
Claim 32
Dependent Claim
25 words
The system of claim 20, further comprising means for gathering acoustical scattering data for construction of the feature space classifier of a known data set.
Claim 33
Dependent Claim
19 words
The system of claim 20, further comprising means for gathering electromagnetic scattering data for input to the first array.
Claim 34
Dependent Claim
19 words
The system of claim 20, further comprising means for gathering acoustical scattering data for input to the first array.
Claim 35
Dependent Claim
13 words
The system of claim 20, wherein the feedback input reaches steady state auto-associatively.
Claim 36
Dependent Claim
13 words
The system of claim 20, wherein the feedback input reaches steady state hetero-associatively.
Claim 37
Dependent Claim
14 words
The system of claim 20, wherein the feedback input reaches steady state cyclic hetero-associatively.
Claim 38
Dependent Claim
11 words
The system of claim 20, wherein the memory matrix is synaptic.
Claim 39
Dependent Claim
11 words
The system of claim 20, wherein the memory matrix is interconnected.
Claim 40
Dependent Claim
14 words
The system of claim 20, wherein the feature space classifier is a sinogram classifier.
Claim 41
Independent Claim
113 words
A method of data analysis comprising the steps of: quantizing a feature space classifier of at least one known data set; associatively storing said quantized feature space classifier in a memory matrix in accordance with a Hebbian model of distributed memory of neural networks; inputting data signals to a first array comprising neural elements; transmitting the input data signals from the neural elements of the first array to the memory matrix for processing; receiving the processed data signals with a second array comprising neural elements; feeding back the signals received by the second array to the first array so that output from the second array becomes feedback input data for the first array.
Claim 42
Independent Claim
113 words
A method of data analysis comprising the steps of: quantizing a feature space classifier of at least one known data set; associatively storing said quantized feature space classifier in a memory matrix in accordance with a Hebbian model of distributed memory of neural networks; inputting data signals to a first array comprising neural elements; transmitting the input data signals from the neural elements of the first array to the memory matrix for processing; receiving the processed data signals with a second array comprising neural elements; feeding back the signals received by the second array to the first array so that output from the second array becomes feedback input data for the first array.
Claim 43
Dependent Claim
13 words
The method of claim 39, wherein the feature space classifier is stored auto-associatively.
Claim 44
Dependent Claim
13 words
The method of claim 39, wherein the feature space classifier is stored hetero-associatively.
Claim 45
Dependent Claim
14 words
The method of claim 39, wherein the feature space classifier is stored cyclic hetero-associatively.
Claim 46
Dependent Claim
11 words
The method of claim 39, wherein the memory matrix is synaptic.
Claim 47
Dependent Claim
11 words
The method of claim 39, wherein the memory matrix is interconnected.
Claim 48
Dependent Claim
13 words
The method of claim 39, wherein the feedback input reaches steady state auto-associatively.
Claim 49
Dependent Claim
13 words
The method of claim 39, wherein the feedback input reaches steady state hetero-associatively.
Claim 50
Dependent Claim
14 words
The method of claim 39, wherein the feedback input reaches steady state cyclic hetero-associatively.
Claim 51
Dependent Claim
13 words
The method of claim 39, wherein the feature space classifier a sinogram classifier.
Claim 52
Independent Claim
119 words
A method of data analysis comprising the steps of: quantizing a feature space classifier of at least one known data set; associatively storing said quantized feature space classifier in a memory matrix in accordance with a Hebbian model of distributed memory of neural networks; inputting data signals to a first array comprising optical neural elements; optically transmitting the input data signals from the optical neural elements of the first array to the memory matrix for optical processing; receiving the optically processed data signals with a second array comprising optical neural elements; feeding back the signals received by the second array to the first array so that output from the second array becomes feedback input data for the first array.
Claim 53
Independent Claim
119 words
A method of data analysis comprising the steps of: quantizing a feature space classifier of at least one known data set; associatively storing said quantized feature space classifier in a memory matrix in accordance with a Hebbian model of distributed memory of neural networks; inputting data signals to a first array comprising optical neural elements; optically transmitting the input data signals from the optical neural elements of the first array to the memory matrix for optical processing; receiving the optically processed data signals with a second array comprising optical neural elements; feeding back the signals received by the second array to the first array so that output from the second array becomes feedback input data for the first array.
Claim 54
Dependent Claim
13 words
The method of claim 49, wherein the feature space classifier is stored auto-associatively.
Claim 55
Dependent Claim
13 words
The method of claim 49, wherein the feature space classifier is stored hetero-associatively.
Claim 56
Dependent Claim
14 words
The method of claim 49, wherein the feature space classifier is stored cyclic hetero-associatively.
Claim 57
Dependent Claim
11 words
The method of claim 49, wherein the memory matrix is synaptic.
Claim 58
Dependent Claim
11 words
The method of claim 49, wherein the memory matrix is interconnected.
Claim 59
Dependent Claim
13 words
The method of claim 49, wherein the feedback input reaches steady state auto-associatively.
Claim 60
Dependent Claim
13 words
The method of claim 49, wherein the feedback input reaches steady state hetero-associatively.
Claim 61
Dependent Claim
14 words
The method of claim 49, wherein the feedback input reaches steady state cyclic hetero-associatively.
Claim 62
Dependent Claim
14 words
The method of claim 49, wherein the feature space classifier is a sinogram classifier.
Claim 63
Dependent Claim
23 words
The system of claim 19 wherein the sinogram classifier is binarized in a unipolar binary matrix and stored in the Hebbian memory matrix.
References Cited (Backward Citations)
US3766532A
Cited
US3766533A
Cited
US4471470A
Cited
US4254476A
Cited
US4488260A
Cited
US4774677A
Cited
US4559643A
Cited
US4470048A
Cited
US4532608A
Cited
US4627029A
Cited
US4586164A
Cited
US4641350A
Cited
US4612666A
Cited
US4660166A
Cited
US4773024A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1994-02-18 | 1994-08-20 | 1995-02-19 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1998-02-18 | 1998-08-20 | 1999-02-19 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2002-02-18 | 2002-08-20 | 2003-02-19 | $7700.00 | Window Closed / Lapsed |