Manuel I Aparicio

US Patent:

20050163347, Jul 28, 2005

Filed:

Jan 14, 2005

Appl. No.:

11/036641

Inventors:

Manuel Aparicio - Chapel Hill NC, US
David Cabana - Cary NC, US

International Classification:

G06K009/00

US Classification:

382103000

Abstract:

A location of a missing object is predicted based on past sightings of objects including the missing object, and a new sighting of the objects except for the missing object. For a respective given object in the objects, the past sightings are memorized based on respective distances of respective remaining objects from the respective given object. Distance-based memorization may take place using an agent or associative memory for a respective given object. Then, for a respective given object, except for the missing object, a distance of the missing object from the respective given object is predicted, based on the past sightings that have been memorized and the new sighting, to obtain candidate locations for the missing object. The candidate locations are then disambiguated, to predict the location of the missing object.

US Patent:

20060095653, May 4, 2006

Filed:

Nov 3, 2004

Appl. No.:

10/980520

Inventors:

James Fleming - Apex NC, US
Brian McGiverin - Richmond VA, US
Manuel Aparicio - Chapel Hill NC, US

International Classification:

G06F 12/00

US Classification:

711108000

Abstract:

Associative memory systems, methods and/or computer program products include a network of networks of associative memory networks. A network of entity associative memory networks is provided, a respective entity associative memory of which includes associations among a respective observer entity and observed entities that are observed by the respective observer entity, based on input documents. A network of feedback associative memory networks includes associations among observed entities for a respective positive and/or negative evaluation for a respective task of a respective user. A network of document associative memory networks includes associations among observed entities in a respective observed input source, such as a respective input document. A network of community associative memory networks includes associations among a respective observer entity, observed entities that are observed by the respective observer entity, and observed tasks of users in which the observer entity was queried. Associations may be observed into and imagined from the network of networks of associative memory networks.

US Patent:

20070033346, Feb 8, 2007

Filed:

Aug 4, 2005

Appl. No.:

11/196871

Inventors:

Michael Lemen - Durham NC, US
James Fleming - Apex NC, US
Manuel Aparicio - Chapel Hill NC, US

International Classification:

G06F 12/00

US Classification:

711128000

Abstract:

Associative matrix compression methods, systems, computer program products and data structures compress an association matrix that contains counts that indicate associations among pairs of attributes. Selective bit plane representations of those selected segments of the association matrix that have at least one count is performed, to allow compression. More specifically, a set of segments is generated, a respective one of which defines a subset, greater than one, of the pairs of attributes. Selective identifications of those segments that have at least one count are stored. The at least one count that is associated with a respective identified segment is also stored as at least one bit plane representation. The at least one bit plane representation identifies a value of the at least one associated count for a bit position of the count that corresponds to the associated bit plane.

US Patent:

20070038838, Feb 15, 2007

Filed:

Aug 9, 2006

Appl. No.:

11/463448

Inventors:

Noel Greis - Chapel Hill NC, US
Jack Olin - Chapel Hill NC, US
Manuel Aparicio - Chapel Hill NC, US

International Classification:

G06F 12/00

US Classification:

711207000

Abstract:

Sensors are configured to repeatedly monitor variables of a physical system during its operation. A novelty detection system is responsive to the sensors and is configured to repeatedly observe into an associative memory, states of associations among the variables that are repeatedly monitored, during a learning phase. The novelty detection system is further configured to thereafter observe at least one state of associations among the variables that are sensed relative to the states of associations that are in the associative memory, to identify a novel state of associations among the variables. The novelty detection system may determine whether the novel state is indicative of normal operation or of a potential abnormal operation. Multiple layers of learning for real-time diagnostics/prognostics also may be provided.

US Patent:

20080097945, Apr 24, 2008

Filed:

Dec 19, 2007

Appl. No.:

11/960292

Inventors:

Noel Greis - Chapel Hill NC, US
Jack Olin - Chapel Hill NC, US
Manuel Aparicio - Chapel Hill NC, US

International Classification:

G06F 15/18

US Classification:

706021000, 706023000

Abstract:

Sensors are configured to repeatedly monitor variables of a physical system during its operation. A novelty detection system is responsive to the sensors and is configured to repeatedly observe into an associative memory, states of associations among the variables that are repeatedly monitored, during a learning phase. The novelty detection system is further configured to thereafter observe at least one state of associations among the variables that are sensed relative to the states of associations that are in the associative memory, to identify a novel state of associations among the variables. The novelty detection system may determine whether the novel state is indicative of normal operation or of a potential abnormal operation. Multiple layers of learning for real-time diagnostics/prognostics also may be provided.

US Patent:

60526793, Apr 18, 2000

Filed:

Sep 11, 1997

Appl. No.:

8/927776

Inventors:

Manuel Aparicio - Chapel Hill NC

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06N 300
G06N 306

US Classification:

706 15

Abstract:

Artificial neural networks include a plurality of artificial neurons and a plurality of Boolean-complete compartments, a respective one of which couples a respective pair of artificial neurons. By providing Boolean-complete compartments, spurious complement memories can be avoided. A Boolean-complete compartment includes a collection of at least four Boolean functions that represent input vectors to the respective pair of artificial neurons. The collection of at least four Boolean functions are selected from sixteen possible Boolean functions that can represent input vectors to the respective pair of artificial neurons. A count for each of the at least four Boolean functions is also provided. The count represents a number of occurrences of each of the at least four Boolean functions in input vectors to the respective pair of artificial neurons. In order to read the artificial neural network, the network also includes a collection of transfer functions, a respective one of which is associated with a respective one the sixteen possible Boolean functions.

US Patent:

20030033265, Feb 13, 2003

Filed:

Aug 9, 2002

Appl. No.:

10/216341

Inventors:

David Cabana - Cary NC, US
Manuel Aparicio - Chapel Hill NC, US
James Fleming - Apex NC, US

International Classification:

G06E001/00
G06E003/00
G06N003/02
G06G007/00
G06F015/18

US Classification:

706/015000

Abstract:

An artificial neuron includes inputs and dendrites, a respective one of which is associated with a respective one of the inputs. A respective dendrite includes a respective power series of weights. The weights in a given power of the power series represent a maximal projection. A respective power also may include at least one switch, to identify holes in the projections. By providing maximal projections, linear scaling may be provided for the maximal projections, and quasi-linear scaling may be provided for the artificial neuron, while allowing a lossless compression of the associations. Accordingly, hetero-associative and/or auto-associative recall may be accommodated for large numbers of inputs, without requiring geometric scaling as a function of input.