Manuel Q Aparicio

US Patent:

57271747, Mar 10, 1998

Filed:

Mar 23, 1992

Appl. No.:

7/855817

Inventors:

Manuel Aparicio - Arlington TX
Roger A. Chang - Irving TX

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06F 3100

US Classification:

395348

Abstract:

A graphical user interface for a computer system that includes one or more intelligent assistants. The interface includes composite icons comprising a graphical representation of a human figure, a representation of a desk, and a mini-icon that associates an assistant with the object it supports. The assistant's desk can be opened to show its contents and the human figure can move from its position next to the desk to a position on the computer display screen next to a suggestions dialog box that displays suggested actions to the user.

US Patent:

53575970, Oct 18, 1994

Filed:

Jun 24, 1991

Appl. No.:

7/720278

Inventors:

Manuel Aparicio - Arlington TX
Samuel E. Otto - Grapevine TX

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06F 1518

US Classification:

395 21

Abstract:

Based on the recognition that transfer functions of Boolean completeness can be expressed as a domain within a periodic function, an architecture of a artificial neuron which is fully generalized in application and capable of rapid learning with minimal memory requirements while maintaining content addressability of memory, is provided. Full functionality of this architecture is demonstrated for an input vector containing two values. Extension to three variables shows the potential for generality of this architecture to N-valued input vectors.

US Patent:

53613260, Nov 1, 1994

Filed:

Dec 31, 1991

Appl. No.:

7/816460

Inventors:

Manuel Aparicio - Arlington TX
Patrice C. Miller - Keller TX
Wade A. Miller - Keller TX

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06F 1518

US Classification:

395 21

Abstract:

An interface for a neural network includes a generalized data translator and a certainty filter in the data path including the neural network for rendering a decision on raw data, possibly from a data processing application. The data translator is controlled with user-definable parameters and procedures contained in a property list in order to manipulate translation, truncation, mapping (including weighting) and other transformations of the raw data. The neuron to which the output of the data translator is applied is controlled by a code index contained in an action list. An external certainty threshold is also provided, preferably by the action list to filter the output of the neural network. The core program used with the ConExNS neurons for system maintenance also includes further core operations and size maintenance operations responsive to commands from the user of an application to cause operations to be performed with in the neural network as well as to create and update the property and action lists.

US Patent:

55175970, May 14, 1996

Filed:

Jun 30, 1993

Appl. No.:

8/085522

Inventors:

Manuel Aparicio - Arlington TX
Samuel E. Otto - Grapevine TX

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06F 1518

US Classification:

395 24

Abstract:

Based on the recognition that transfer functions of Boolean completeness can be expressed as a domain within a periodic function, an architecture of a artificial neuron which is fully generalized in application and capable of rapid learning with minimal memory requirements while maintaining content addressability of memory, is provided. Full functionality of this architecture is demonstrated for an input vector containing two values. Extension to three variables shows the potential for generality of this architecture to N-valued input vectors.