Yang J Zhang

US Patent:

20210117508, Apr 22, 2021

Filed:

Oct 20, 2019

Appl. No.:

16/658120

Inventors:

- Armonk NY, US
Mo Yu - White Plains NY, US
Yang Zhang - Cambridge MA, US
Tommi S. Jaakkola - Cambridge MA, US

International Classification:

G06F 17/27
G06F 17/18
G06K 9/62
G06N 20/20
G06N 3/04
G06N 3/08

Abstract:

A method and system of training a natural language processing network are provided. A corpus of data is received and one or more input features selected therefrom by a generator network. The one or more selected input features from the generator network are received by a first predictor network and used to predict a first output label. A complement of the selected input features from the generator network are received by a second predictor network and used to predict a second output label.

US Patent:

20210117772, Apr 22, 2021

Filed:

Oct 20, 2019

Appl. No.:

16/658122

Inventors:

- ARMONK NY, US
Mo Yu - White Plains NY, US
Yang Zhang - Cambridge MA, US
Tommi S. Jaakkola - Cambridge MA, US

International Classification:

G06N 3/08
G06N 3/04

Abstract:

A method and system of determining an output label rationale are provided. A first generator receives a first class of data and selects one or more input features from the first class of data. A first predictor receives the one or more selected input features from the first generator and predicts a first output label. A second generator receives a second class of data and selects one or more input features from the second class of data. A second predictor receives the one or more selected input features from the second generator and predicts a second output label. A discriminator receives the first and second output labels and determines whether the selected one or more input features from the first class of data or the selected features of the one or more input features from the second class of data, more accurately represents the first output label.

US Patent:

20200278320, Sep 3, 2020

Filed:

Feb 28, 2020

Appl. No.:

16/804066

Inventors:

- Morris Plains NJ, US
Guangli XIE - Morris Plains NJ, US
Zhiguo WANG - Morris Plains NJ, US
Bo CHEN - Morris Plains NJ, US
Yang ZHANG - Morris Plains NJ, US

International Classification:

G01N 27/66

Abstract:

The present utility model relates to a device for improving gas detection in a photoionization detector. A gas detector is provided. The device reduces interference of photoelectric noise on the reading of the gas detector for target gases such as volatile organic compounds.

US Patent:

20200175281, Jun 4, 2020

Filed:

Nov 30, 2018

Appl. No.:

16/206683

Inventors:

- Armonk NY, US
Sijia Liu - YORKTOWN HEIGHTS NY, US
Yang Zhang - YORKTOWN HEIGHTS NY, US

International Classification:

G06K 9/00
G06K 9/32
G06K 9/62
G06F 17/16
G06F 17/11

Abstract:

A method (and structure and computer product) of temporal action localization in video data includes receiving a stream of video data and determining all proposals in the video data stream, the proposals being candidate regions for temporal action in the video data stream. Values for a pair-wise relation function are calculated for relating the proposals, wherein the pair-wise relation function calculates a scalar value representing a pair-wise relation weight for pairs of the proposals.

US Patent:

20200025733, Jan 23, 2020

Filed:

Jul 19, 2019

Appl. No.:

16/516368

Inventors:

- Morris Plains NJ, US
Xiaoyi YAN - Morris Plains NJ, US
Qinghui MU - Morris Plains NJ, US
Na WEI - Morris Plains NJ, US
Lei XIAO - Morris Plains NJ, US
Yang ZHANG - Morris Plains NJ, US
Huiping YAO - Morris Plains NJ, US
Feng LIANG - Morris Plains NJ, US

International Classification:

G01N 33/00

Abstract:

The present invention relates to a method for detecting a gas concentration using a gas detection device, comprising: determining a first relationship between a baseline drift of the gas detection device with respect to a gas concentration and an environmental temperature and performing, based on the baseline drift of the gas detection device with respect to a gas having a first temperature, a first compensation on a gas concentration output value of the gas having the first temperature determined by the gas detection device. With such a method, a gas concentration check result is more accurate, and the gas detection device can be applied to a wider range of application scenarios.