Patent US2973571A successfully refreshed from Google Patents.
Patent US2168220A successfully refreshed from Google Patents.
Patent US2444433A successfully refreshed from Google Patents.
Patent US5450529A successfully refreshed from Google Patents.
US5450529A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Neural network shell for application programs
Assignee: International Business Machines Corp
•
Filing: 1993-06-11
•
Granted: 1995-09-12
•
Expires: 2013-06-11
Abstract
Abstract A neural network shell has a defined interface to an application program. By interfacing with the neural network shell, any application program becomes a neural network application program. The neural network shell contains a set of utility programs that transfers data into and out of a neural network data structure. This set of utility programs allows an application program to define a new neural network model, create a neural network data structure, train a neural network, and run a neural network. Once trained, the neural network data structure can be transported to other computer systems or to application programs written in different computing languages running on similar or different computer systems.
Inventors
- 👤 Joseph P. Bigus
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-01 18:24
CPC Classifications
G; G06; G06N; G06N3/00; G06N3/02; G06N3/04; G06N3/0499; G06N3/08; G06N3/09
Claims Analysis
Total Claims: 8
Claim 1
Independent Claim
144 words
A method in a neural network shell of creating a neural network data structure for a neural network, comprising the machine-executed steps of: selecting a neural network model from a plurality of defined neural network models for said neural network, wherein said neural network data structure is common and generic to all of said plurality of neural network models, and wherein said neural network data structure comprises a network size parameter field containing a plurality of network size parameters specific to said selected neural network model; creating a default neural network data structure corresponding to said neural network model selected in said selecting step by inputting initial values for a plurality of data arrays into said neural network data structure; prompting for a plurality of parameters specific to said neural network; and inputting said plurality of parameters into said default neural network data structure.
Claim 2
Independent Claim
144 words
A method in a neural network shell of creating a neural network data structure for a neural network, comprising the machine-executed steps of: selecting a neural network model from a plurality of defined neural network models for said neural network, wherein said neural network data structure is common and generic to all of said plurality of neural network models, and wherein said neural network data structure comprises a network size parameter field containing a plurality of network size parameters specific to said selected neural network model; creating a default neural network data structure corresponding to said neural network model selected in said selecting step by inputting initial values for a plurality of data arrays into said neural network data structure; prompting for a plurality of parameters specific to said neural network; and inputting said plurality of parameters into said default neural network data structure.
Claim 3
Dependent Claim
42 words
The method in a neural network shell of creating a neural network data structure of claim 1, wherein said plurality of network size parameters comprise a number of inputs parameter, an number of hidden inputs parameter, and a number of outputs parameter.
Claim 4
Independent Claim
141 words
A method in a neural network shell of creating a neural network data structure for a neural network, comprising the machine-executed steps of: selecting a neural network model from a plurality of defined neural network models for said neural network, wherein said neural network data structure is common and genetic to all of said plurality of neural network models, and wherein said neural network data structure comprises a training parameter field containing a plurality of training parameters specific to said neural network model; creating a default neural network data structure corresponding to said neural network model selected in said selecting step by inputting initial values for a plurality of data arrays into said neural network data structure; prompting for a plurality of parameters specific to said neural network; and inputting said plurality of parameters into said default neural network data structure.
Claim 5
Independent Claim
141 words
A method in a neural network shell of creating a neural network data structure for a neural network, comprising the machine-executed steps of: selecting a neural network model from a plurality of defined neural network models for said neural network, wherein said neural network data structure is common and genetic to all of said plurality of neural network models, and wherein said neural network data structure comprises a training parameter field containing a plurality of training parameters specific to said neural network model; creating a default neural network data structure corresponding to said neural network model selected in said selecting step by inputting initial values for a plurality of data arrays into said neural network data structure; prompting for a plurality of parameters specific to said neural network; and inputting said plurality of parameters into said default neural network data structure.
Claim 6
Dependent Claim
35 words
A method in a neural network shell of creating a neural network data structure of claim 3, wherein said plurality of training parameters comprise a learn rate parameter, a momentum parameter, and a tolerance parameter.
Claim 7
Independent Claim
141 words
A method in a neural network shell of creating a neural network data structure for a neural network, comprising the machine-executed steps of: selecting a neural network model from a plurality of defined neural network models for said neural network, wherein said neural network data structure is common and generic to all of said plurality of neural network models, and wherein said neural network data structure comprises a current state field indicating whether said values in a plurality of data arrays are locked; creating a default neural network data structure corresponding to said neural network model selected in said selecting step by inputting initial values for a plurality of data arrays into said neural network data structure; prompting for said plurality of parameters specific to said neural network; and inputting said plurality of parameters into said default neural network data structure.
Claim 8
Independent Claim
141 words
A method in a neural network shell of creating a neural network data structure for a neural network, comprising the machine-executed steps of: selecting a neural network model from a plurality of defined neural network models for said neural network, wherein said neural network data structure is common and generic to all of said plurality of neural network models, and wherein said neural network data structure comprises a current state field indicating whether said values in a plurality of data arrays are locked; creating a default neural network data structure corresponding to said neural network model selected in said selecting step by inputting initial values for a plurality of data arrays into said neural network data structure; prompting for said plurality of parameters specific to said neural network; and inputting said plurality of parameters into said default neural network data structure.
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) | 1998-09-11 | 1999-03-13 | 1999-09-12 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2002-09-11 | 2003-03-13 | 2003-09-12 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2006-09-11 | 2007-03-13 | 2007-09-12 | $7700.00 | Window Closed / Lapsed |