James D Murdock

US Patent:

8510296, Aug 13, 2013

Filed:

Sep 23, 2011

Appl. No.:

13/242290

Inventors:

James J. Fan - Hawthorne NY, US
David A. Ferrucci - Yorktown Heights NY, US
David C. Gondek - Hawthorne NY, US
Aditya A. Kalyanpur - Westwood NJ, US
Adam P. Lally - Cold Spring NY, US
James W. Murdock - Millwood NY, US
Wlodek W. Zadrozny - Tarrytown NY, US

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06F 17/30

US Classification:

707728, 707722, 707736, 706 12, 706 14

Abstract:

A system, method and computer program product for automatically estimating the confidence of a detected LAT to provide a more accurate overall score for an obtained candidate answer. A confidence “score” or value of each detected LAT is obtained, and the system and method performs combining the confidence score with a degree of match between a LAT and an AnswerType of the candidate answer to provide improved overall score for the candidate answer.

US Patent:

8600986, Dec 3, 2013

Filed:

Aug 29, 2012

Appl. No.:

13/597795

Inventors:

James J. Fan - Hawthorne NY, US
David A. Ferrucci - Yorktown Heights NY, US
David C. Gondek - Hawthorne NY, US
Aditya A. Kalyanpur - Westwood NJ, US
Adam P. Lally - Cold Spring NY, US
James W. Murdock - Millwood NY, US
Wlodek W. Zadrozny - Tarrytown NY, US

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06F 17/30

US Classification:

707728, 707722, 707736, 706 12, 706 14

Abstract:

A system, method and computer program product for automatically estimating the confidence of a detected LAT to provide a more accurate overall score for an obtained candidate answer. A confidence “score” or value of each detected LAT is obtained, and the system and method performs combining the confidence score with a degree of match between a LAT and an AnswerType of the candidate answer to provide improved overall score for the candidate answer.

US Patent:

20130182442, Jul 18, 2013

Filed:

Mar 6, 2013

Appl. No.:

13/786739

Inventors:

Hayward Industries, Inc. - Elizabeth NJ, US
James Carter - East Greenwich RI, US
James Murdock - Peace Dale RI, US
Joe Diorio - North Providence RI, US
Steven Mitchell - Chepachet RI, US

Assignee:

Hayward Industries, Inc. - Elizabeth NJ

International Classification:

F21V 29/00

US Classification:

362294

Abstract:

An underwater light having a sealed polymer housing includes a rear housing component formed at least in part from a thermally conductive and electrically insulative material, an electronic assembly having at least one light-emitting element mounted thereto, the electronic assembly in thermal communication with the rear housing component, and a lens mounted to the rear housing component and forming a watertight seal therebetween, the lens and the rear housing component enclosing the electronic assembly. At least a portion of the rear housing component conducts heat away from the electronic assembly to cool the electronic assembly.

US Patent:

20130282363, Oct 24, 2013

Filed:

Jun 18, 2013

Appl. No.:

13/920513

Inventors:

David A. Ferrucci - Yorktown Heights NY, US
David C. Gondek - Providence RI, US
Aditya A. Kalyanpur - Westwood NJ, US
Adam P. Lally - Cold Spring NY, US
James W. Murdock - Millwood NY, US
Wlodek W. Zadrozny - Tarrytown NY, US

International Classification:

G06F 17/28

US Classification:

704 9

Abstract:

A system, method and computer program product for automatically estimating the confidence of a detected LAT to provide a more accurate overall score for an obtained candidate answer. A confidence “score” or value of each detected LAT is obtained, and the system and method performs combining the confidence score with a degree of match between a LAT and an AnswerType of the candidate answer to provide improved overall score for the candidate answer.

US Patent:

50440217, Sep 3, 1991

Filed:

Aug 18, 1989

Appl. No.:

7/395733

Inventors:

James Murdock - New York NY

Assignee:

Endless Pools, Inc. - New York NY

International Classification:

E04H 400

US Classification:

4488

Abstract:

A continuous swimming apparatus is provided which minimizes power requirements by providing higher water velocity through that portion of the swimming area in which the swimmer is located, and lower velocity in unused portions of the tank. This water velocity gradient is produced by an arrangement of turning vanes in the recirculation paths of the apparatus. The water velocity may be varied by adjusting hydraulic fluid flow to hydraulic motors which drive propellers for circulating the water through the apparatus.

US Patent:

46725180, Jun 9, 1987

Filed:

Jul 30, 1986

Appl. No.:

6/890440

Inventors:

James H. Murdock - Denville NJ

Assignee:

American Telephone and Telegraph Co., AT&T Bell Labs - Murray Hill NJ

International Classification:

H02M 3335

US Classification:

363 21

Abstract:

A switching converter in which current mode voltage regulation is implemented includes circuitry to add ramp compensation to the sensed current signal at light load and reduce or disable this ramp signal compensation at heavy load. This load dependent ramp signal improves the stability of operation of the converter and maintains its inherent current limit performance over a wide range of loading. An alternative connection allows for disabling the current sense signal and hence, transforming the current mode to voltage mode control under light load.

US Patent:

20190213502, Jul 11, 2019

Filed:

Jan 8, 2018

Appl. No.:

15/863980

Inventors:

- ARMONK NY, US
James W. Murdock - Amawalk NY, US

International Classification:

G06N 99/00

Abstract:

A computer accesses a machine learning model and multiple samples, each classified with a separate original class of multiple classes within training data used to train the machine learning model to identify each of the classes. The computer generates multiple synthetic samples, each comprising a sample distorted to induce the machine learning model to misclassify the sample to a different class from the original class. The computer creates a synthetic sample signature, for use in verifying the identity of the machine learning model at runtime, from the synthetic samples and a matrix of returned class labels each identifying one of the classes, determined from actual classifications of each the synthetic samples in response to running the synthetic samples on the machine learning model.

US Patent:

20190213503, Jul 11, 2019

Filed:

Jan 8, 2018

Appl. No.:

15/863982

Inventors:

- Armonk NY, US
James W. Murdock - Amawalk NY, US

International Classification:

G06N 99/00
G06F 9/54
G06F 17/30

Abstract:

A computer querying an application programming interface with each of multiple synthetic samples, each of the synthetic samples representing a separate sample assigned an original class from among multiple classes classified by a particular machine learning model and distorted to induce the particular machine learning model to misclassify the separate sample as a different class from among the classes. The computer accumulating, by the computer, a score of a number of results returned by the application programming interface that match an expected class label assignment of the different class for each of the synthetic samples. The computer, in response to the score exceeding a threshold, verifying, by the computer, that a service provided by the application programming interface is running the particular machine learning model.