US5109351A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Learning device and method
Assignee: Texas Instruments Inc
•
Filing: 1989-08-21
•
Granted: 1992-04-28
•
Expires: 2009-08-21
Abstract
Abstract Layered arrays of nearest-neighbor connected computation cells plus an error computation layer provide a learning network.
Inventors
- 👤 L. Ray Simar, Jr.
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-04 05:58
CPC Classifications
G; G06; G06N; G06N3/00; G06N3/02; G06N3/04; G06N3/0499; G06N3/08; G06N3/09
Claims Analysis
Total Claims: 9
Claim 1
Independent Claim
153 words
A learning network, comprising: (a) a plurality of computational layers labelled by index k with 0≦k≦K-1 for a positive integer K and a sequence of positive integers N k , each of said k layers including an array of computation cells arranged into rows and columns and labelled (i,j) with 0≦i≦N k -1 and 0≦j≦N k-1 -1, each of said cells connected within layer k to its nearest neighbors only, (b) interconnection from cell (i, N k-1 -1) of layer k to cell (0,i) of layer k+1 for each i; (c) interconnection from cell (N k+1 -1, i) of layer k+1 to cell (i,0) of layer k for each i; (d) external input connections for computation cells (0,j) of layer 0; and (e) an error computation layer with inputs connected from cell (i,N K-1 -1) for each i of layer K-1 and outputs connected to cell (i,0) for each i of layer K-1.
Claim 2
Dependent Claim
153 words
A learning network, comprising: (a) a plurality of computational layers labelled by index k with 0≦k≦K-1 for a positive integer K and a sequence of positive integers N k , each of said k layers including an array of computation cells arranged into rows and columns and labelled (i,j) with 0≦i≦N k -1 and 0≦j≦N k-1 -1, each of said cells connected within layer k to its nearest neighbors only, (b) interconnection from cell (i, N k-1 -1) of layer k to cell (0,i) of layer k+1 for each i; (c) interconnection from cell (N k+1 -1, i) of layer k+1 to cell (i,0) of layer k for each i; (d) external input connections for computation cells (0,j) of layer 0; and (e) an error computation layer with inputs connected from cell (i,N K-1 -1) for each i of layer K-1 and outputs connected to cell (i,0) for each i of layer K-1.
Claim 3
Dependent Claim
20 words
The network of claim 1, wherein: (a) each of said computation cells includes a memory for storing a state variable.
Claim 4
Dependent Claim
18 words
The network of claim 1, wherein: (a) each of said rows of computation cells provides partial sum computation.
Claim 5
Dependent Claim
18 words
The network of claim 1, wherein: (a) each of said columns of computation cells provides partial sum computation.
Claim 6
Dependent Claim
63 words
The network of claim 1, wherein: (a) for each layer k each of said (i,N k-1 -1) cells includes a forward output cell and an arithmetic cell, each of said (N k -1,j) cells includes a backward output cell and an arithmetic cell, and each of said (i,j) cells includes an arithmetic cell, wherein all of said arithmetic cells are structurally the same.
Claim 7
Dependent Claim
21 words
The network of claim 5, wherein: (a) each of said forward output cells including a memory for storing a semilinear function.
Claim 8
Dependent Claim
106 words
The network of claim 5, wherein: (a) each of said arithmetic cells includes first, second, third, and fourth inputs and first, second, third, and fourth outputs with data entering said first input passing unchanged out said first output, data entering said second input passing unchanged out said second output, data entering said third input modified by addition of the product of data entering said second input and a stored state variable and passing out said third output, and data entering said fourth input modified by addition of the product of data entering said first input and said stored state variable and passing out said fourth output.
Claim 9
Dependent Claim
39 words
The network of claim 7, wherein: (a) each of said arithmetic cells modifies said stored state variable by addition of the product of data entering said first input and data entering said second input multiplied by a negative constant.
References Cited (Backward Citations)
US4807168A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1995-04-28 | 1995-10-28 | 1996-04-28 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1999-04-28 | 1999-10-28 | 2000-04-28 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2003-04-28 | 2003-10-28 | 2004-04-28 | $7700.00 | Window Closed / Lapsed |