Search

Paul A Hospers

from Rochester, MN
Age ~66
Get Report
Also known as:
Paul Alan Hospers
Phone and address:
5704 Longboat Rd, Rochester, MN 55901
(507) 285-0689
Related to:
Margaret M O'HaireRolina Vermeer
Connected to:
Terrie L Hospers, 63Cecilia Hospidales, 44Nicholas A Hospidales, 32Matt J Hospidor, 53Justin F Hospie, 41Barbara C Hospod, 63Edward D Hospodar, 65John J Hospodar, 58Mark E Hospodar, 70Rosemary J Hospodar, 71

Paul Hospers Phones & Addresses

  • 5704 Longboat Rd, Rochester, MN 55901 (507) 285-0689
  • Overland Park, KS
  • Yorktown, IN

Resumes

Resumes

Paul Hospers Photo 1

Software Programmer

View page
Location:
Rochester, MN
Industry:
Information Technology And Services
Work:
Ibm
Software Programmer
Education:
Hope College 1977 - 1980
Bachelors, Bachelor of Arts, Mathematics, Computer Science
Paul Hospers Photo 2

Paul Hospers

View page
Paul Hospers Photo 3

Paul Hospers

View page

Publications

Us Patents

Enhanced Neural Network Shell For Application Programs

View page
US Patent:
54448247, Aug 22, 1995
Filed:
Aug 3, 1993
Appl. No.:
8/101526
Inventors:
Shawn M. Austvold - Rochester MN
Joseph P. Bigus - Rochester MN
Jonathan D. Henckel - Rochester MN
Paul A. Hospers - Rochester MN
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G06F 1518
US Classification:
395 76
Abstract:
An enhanced neural network shell for application programs is disclosed. The user is prompted to enter in non-technical information about the specific problem type that the user wants solved by a neural network. The user also is prompted to indicate the input data usage information to the neural network. Based on this information, the neural network shell creates a neural network data structure by automatically selecting an appropriate neural network model and automatically generating an appropriate number of inputs, outputs, and/or other model-specific parameters for the selected neural network model. The user is no longer required to have expertise in neural network technology to create a neural network data structure.

Apparatus And Method For Facilitating Use Of A Neural Network

View page
US Patent:
53176766, May 31, 1994
Filed:
Dec 3, 1992
Appl. No.:
7/986889
Inventors:
Shawn M. Austvold - Rochester MN
Joseph P. Bigus - Rochester MN
Jonathan D. Henckel - Rochester MN
Paul A. Hospers - Rochester MN
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G06F 1518
US Classification:
395 26
Abstract:
A neural network development utility assists a developer in generating one or more filters for data to be input to or output from a neural network. A filter is a device which translates data in accordance with a data transformation definition contained in a translate template. Source data for the neural network may be expressed in any arbitrary combination of symbolic or numeric fields in a data base. The developer selects those fields to be used from an interactive menu. The utility scans the selected field entries in the source data base to identify the logical type of each field, and creates a default translate template based on this scan. Numeric data is automatically scaled. The developer may use the default template, or edit it from an interactive editor. When editing the template, the developer may select from a menu of commonly used neural network data formats, and from a menu of commonly used primitive mathematical operations. The developer may interactively define additional filters to perform data transformations in series, thus achieving more complex mathematical operations on the data.

Enhanced Neural Network Shell For Application Programs

View page
US Patent:
52356736, Aug 10, 1993
Filed:
Apr 18, 1991
Appl. No.:
7/687582
Inventors:
Shawn M. Austvold - Rochester MN
Joseph P. Bigus - Rochester MN
Jonathan D. Henckel - Rochester MN
Paul A. Hospers - Rochester MN
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G06F 1518
US Classification:
395 76
Abstract:
An enhanced neural network shell for application programs is disclosed. The user is prompted to enter in non-technical information about the specific problem type that the user wants solved by a neural network. The user also is prompted to indicate the input data usage information to the neural network. Based on this information, the neural network shell creates a neural network data structure by automatically selecting an appropriate neural network model and automatically generating an appropriate number of inputs, outputs, and/or other model-specific parameters for the selected neural network model. The user is no longer required to have expertise in neural network technology to create a neural network data structure.

Data Processing System Graphical User Interface Which Emulates Printed Material

View page
US Patent:
54637252, Oct 31, 1995
Filed:
Dec 31, 1992
Appl. No.:
7/998988
Inventors:
Jonathan D. Henckel - Rochester MN
Paul A. Hospers - Rochester MN
Assignee:
International Business Machines Corp.
International Classification:
G06F 1500
US Classification:
395155
Abstract:
An interface for making information available to a user provides a display similar to a printed book or magazine. In order to "turn the page" of the displayed book, the user touches the screen with his hand or a pointing device, and moves it across the screen. Movement across the screen, while touching the screen, causes an animated turning of the page of the displayed printed material. This page turning technique is very similar to the turning of a page with an actual book or magazine.

Program Product For Facilitating Use Of A Neural Network

View page
US Patent:
55465056, Aug 13, 1996
Filed:
May 27, 1994
Appl. No.:
8/251532
Inventors:
Shawn M. Austvold - Rochester MN
Joseph P. Bigus - Rochester MN
Jonathan D. Henckel - Rochester MN
Paul A. Hospers - Rochester MN
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G06F 1518
US Classification:
395 26
Abstract:
A neural network development utility assists a developer in generating one or more filters for data to be input to or output from a neural network. A filter is a device which translates data in accordance with a data transformation definition contained in a translate template. Source data for the neural network may be expressed in any arbitrary combination of symbolic or numeric fields in a data base. The developer selects those fields to be used from an interactive menu. The utility scans the selected field entries in the source data base to identify the logical type of each field, and creates a default translate template based on this scan. Numeric data is automatically scaled. The developer may use the default template, or edit it from an interactive editor. When editing the template, the developer may select from a menu of commonly used neural network data formats, and from a menu of commonly used primitive mathematical operations. The developer may interactively define additional filters to perform data transformations in series, thus achieving more complex mathematical operations on the data.
Control profile
Paul A Hospers from Rochester, MN, age ~66 Get Report