Yu Liang

US Patent:

20180055825, Mar 1, 2018

Filed:

Aug 24, 2017

Appl. No.:

15/685164

Inventors:

Yu Liang - San Francisco CA, US
Susan D. Bromley - San Francisco CA, US
Keith Orford - Doylestown PA, US

International Classification:

A61K 31/433
A61K 31/5377
A61K 31/496
A61K 31/454
A61K 31/4245
A61K 31/501
A61K 31/506
C12Q 1/68
A61K 45/06

Abstract:

The invention relates to method of treating a disease or disorder (e.g., such as cancer) in a subject, comprising administering to the subject heterocyclic compounds and pharmaceutical preparations described herein, if the subject is determined to possess at least one G allele at single nucleotide polymorphism (SNP) rs6983267.

US Patent:

20160048754, Feb 18, 2016

Filed:

Aug 24, 2015

Appl. No.:

14/834274

Inventors:

- Mountain View CA, US
Yu Liang - Santa Clara CA, US
Ke Yang - Cupertino CA, US
Kai Chen - San Bruno CA, US

International Classification:

G06N 3/04
G06F 17/30
G06N 7/00
G06F 3/0484

Abstract:

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scoring concept terms using a deep network. One of the methods includes receiving an input comprising a plurality of features of a resource, wherein each feature is a value of a respective attribute of the resource; processing each of the features using a respective embedding function to generate one or more numeric values; processing the numeric values using one or more neural network layers to generate an alternative representation of the features, wherein processing the floating point values comprises applying one or more non-linear transformations to the floating point values; and processing the alternative representation of the input using a classifier to generate a respective category score for each category in a pre-determined set of categories, wherein each of the respective category scores measure a predicted likelihood that the resource belongs to the corresponding category.

US Patent:

20140279774, Sep 18, 2014

Filed:

Mar 13, 2013

Appl. No.:

13/802462

Inventors:

- Mountain View CA, US
Yu Liang - Santa Clara CA, US
Ke Yang - Cupertino CA, US
Kai Chen - Brisbane CA, US

Assignee:

Google Inc. - Mountain View CA

International Classification:

G06N 3/02

US Classification:

706 20

Abstract:

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scoring concept terms using a deep network. One of the methods includes receiving an input comprising a plurality of features of a resource, wherein each feature is a value of a respective attribute of the resource; processing each of the features using a respective embedding function to generate one or more numeric values; processing the numeric values using one or more neural network layers to generate an alternative representation of the features, wherein processing the floating point values comprises applying one or more non-linear transformations to the floating point values; and processing the alternative representation of the input using a classifier to generate a respective category score for each category in a pre-determined set of categories, wherein each of the respective category scores measure a predicted likelihood that the resource belongs to the corresponding category.