 |
|
|
|
|
|
 Title: |
US5450529:
Neural network shell for application programs
[ Derwent Title ]
|
| Country: |
US United States of America
|
| |
| Inventor: |
Bigus, Joseph P.; Rochester, MN
|
| Assignee: |
International Business Machines Corporation, Armonk, NY
other patents from INTERNATIONAL BUSINESS MACHINES CORPORATION (280070) (approx. 44,393)
News, Profiles, Stocks and More about this company
|
| Published / Filed: |
1995-09-12
/ 1993-06-11
|
| Application Number: |
US1993000075370
|
| IPC Code: |
Advanced:
G06N 3/04;
Core:
G06N 3/00;
IPC-7:
G06F 15/18;
|
| ECLA Code: |
G06N3/04;
|
| U.S. Class: |
Current:
706/044;
Original:
395/076;
395/012;
395/021;
395/022;
|
| Field of Search: |
395/076,21,22,12
|
| Priority Number: |
|
| 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.
|
| Attorney, Agent or Firm: |
Rose, Curtis G. ;
Gamon, Owen J. ;
|
| Primary / Asst. Examiners: |
Downs, Robert W.;
|
| Maintenance Status: |
E1 Expired Check current status
|
| INPADOC Legal Status: |
Show legal status actions
Family Legal Status Report
|
|
|
|
|
|
|
| Parent Case: |
This is a divisional of application Ser. No. 07/849,116 filed on Mar. 10, 1992, now U.S. Pat. No. 5,222,196, which is a divisional of application Ser. No. 07/482,450, filed on Feb. 20, 1990, now issued as U.S. Pat. No. 5,142,665.
|
| Designated Country: |
CH DE ES FR GB IT LI NL SE
|
| Family: |
Show 14 known family members
|
First Claim:
Show all 5 claims |
What is claimed is:
1. 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.
|
| Background / Summary: |
Show background / summary
|
| Drawing Descriptions: |
Show drawing descriptions
|
| Description: |
Show description
|
| Forward References: |
Show 2 U.S. patent(s) that reference this one
|
|
Nominate this for the Gallery...
