Work Files Saved Searches
   My Account                                                  Search:   Quick/Number   Boolean   Advanced   Derwent    Help   


 The Delphion Integrated View
  Buy Now:   Buy PDF- 35pp  PDF  |   File History  |   Other choices   
  Tools:  Citation Link  |  Add to Work File:    
  View:  Expand Details   |  INPADOC   |  Jump to: 
  Go to:  Derwent  
 Email this to a friend  Email this to a friend 
       
Title: US5615306: Neural network shell for application programs
[ Derwent Title ]

Country: US United States of America

View Images High
Resolution

 Low
 Resolution

 
35 pages

 
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: 1997-03-25 / 1995-06-02

Application Number: US1995000459053
IPC Code: Advanced: G06N 3/04;
Core: G06N 3/00;
IPC-7: G06F 15/18;

U.S. Class: Current: 706/044; 706/060;
Original: 395/026;

Field of Search: 395/011,21,22,23,26,76

Priority Number:
1995-06-02  US1995000459053
1993-06-11  US1993000075370
1992-03-10  US1992000849116
1990-02-20  US1990000482450

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: Gamon, Owen J. ; Rose, Curtis G. ;

Primary / Asst. Examiners: Downs, Robert W.;

Maintenance Status: E3 Expired  Check current status

INPADOC Legal Status: Show legal status actions          Buy Now: Family Legal Status Report

       
Related Applications:
Application Number Filed Patent Pub. Date  Title
US1993000075370 1993-06-11    1995-09-12  Neural network shell for application programs
US1992000849116 1992-03-10    1993-06-22  Neural network shell for application programs
US1990000482450 1990-02-20    1992-08-25  Neural network shell for application programs


       
Parent Case:     This is a divisional of application Ser. No. 08/075,370 filed Jun. 11, 1993, now issued as U.S. Pat. No. 5,450,529 which is a divisional of application Ser. No. 07/849,116 filed on Mar. 10, 1992, now issued as U.S. Pat. No. 5,222,196, which was 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 18 claims		 What is claimed is:     1. A method of transporting a neural network having an input and an output for a result from a first computer system having first storage and running a first operating system, to a second computer system having second storage and running a second operating system, said method comprising the steps of:
  • said first computer system creating a neural network data structure wherein the neural network data structure defines a structure and organization of a plurality of data arrays, wherein the plurality of data arrays have data types and an order within the neural network data structure, wherein the neural network data structure is common and generic to all of a plurality of defined neural network models, and wherein the plurality of data arrays have data values specific to a selected one of the plurality of defined neural network models;
  • said first computer system teaching said neural network by presenting training data at said input of said neural network and repeatedly adjusting the values of said plurality of data arrays until said result at said output is within tolerance of a correct result;
  • copying said neural network data structure from said first storage in said first computer system to said second storage in said second computer system, wherein said second operating system has a different architecture from said first operating system; and
  • said second computer system running said neural network by presenting actual data at said input and retrieving the result from said output of said neural network.
    •


Background / Summary: Show background / summary

Drawing Descriptions: Show drawing descriptions

Description: Show description

       
U.S. References: Go to Result Set: No U.S. references   |  No patents reference this one   |   Backward references (0)

       
Foreign References: None

Other Abstract Info: DERABS G91-254543

Other References:
  • P. Koikkalainen and E. Oja, "Specification and Implementation Environment for Neural Networks Using Communicating Sequential Processes," IEEE Int'l. Conf. on Neural Networks, pp. I-533 to I-540. Jul. 1988.
  • G. Works, "The Creation of Delta: A New Concept in ANS Processing," 1988 IEEE Int'l. Conf. on Neural Networks, pp. II-159 to II-164. Jul. 1988.
  • G. Whittington and C. Spracklen, "ANDS: A Second Generation Neural Network Development System," CONPAR '88, pp. 84-91. Sep. 1988.
  • J. McClelland and D. Rumelhart, Explorations in Parallel Distributed Processing--A Handbook of Models, Programs, and Exercises, The MIT Press, pp. 1-10, 137-152, 245-271. Dec. 1988.
  • R. Eberhart, et al., "CASENET: A Neural Network Tool for EEG Waveform Classification," 1989 Symp. on Computer-Based Medical Systems, pp. 60-68. Jun. 1989.
  • T. Korb and A. Zell, "A Declarative Neural Network Description Language," Microprocessing and Microprogramming, pp. 181-188. Aug. 1989. (8 pages) Cited by 8 patents
  • J. Nijhuis, "Structure and Application of NNSIM: a general-purpose Neural Network SIMulator," Microprocessing and Microprogramming, pp. 189-194. Aug. 1989. (6 pages) Cited by 10 patents
  • R. Brause, "Neural Network Simulation using INES," Tools for Artificial Intelligence, pp. 556-561. Oct. 1989.
  • "Neural-Network Vendors and Features," Al Expert, pp. 60-61. Dec. 1989.
  • P. Chen, The Neural Shell: A Neural Networks Simulator, Masters Thesis, Ohio State University, 87 pages. Dec. 1989.
  • F. Derfler, Jr., "Building workgroup solutions: low-cost LANs," PC Magazine, v. 8, N. 6, pp. 94(22). Mar. 1989.


    • Inquire Regarding Licensing

    Powered by Verity
    Plaques from Patent Awards      Gallery of Obscure PatentsNominate this for the Gallery...

    Thomson Reuters Copyright © 1997-2010 Thomson Reuters 
    Subscriptions  |  Web Seminars  |  Privacy  |  Terms & Conditions  |  Site Map  |  Contact Us  |  Help