The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Apr. 27, 2021

Filed:

Aug. 11, 2017
Applicant:

Microsoft Technology Licensing, Llc, Redmond, WA (US);

Inventors:

Benjamin Hoan Le, San Jose, CA (US);

Saurabh Kataria, Newark, CA (US);

Nadia Fawaz, Santa Clara, CA (US);

Aman Grover, Sunnyvale, CA (US);

Guoyin Wang, Durham, NC (US);

Assignee:
Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06N 20/00 (2019.01); G06N 3/08 (2006.01); H04L 29/08 (2006.01); G06Q 10/10 (2012.01); G06F 3/0482 (2013.01); G06F 16/958 (2019.01); G06F 16/9535 (2019.01); G06F 16/906 (2019.01); G06F 16/901 (2019.01); G06N 3/04 (2006.01); G06N 5/00 (2006.01); G06N 20/20 (2019.01); G06Q 50/00 (2012.01);
U.S. Cl.
CPC ...
G06N 20/00 (2019.01); G06F 3/0482 (2013.01); G06F 16/906 (2019.01); G06F 16/9024 (2019.01); G06F 16/958 (2019.01); G06F 16/9535 (2019.01); G06N 3/0427 (2013.01); G06N 3/08 (2013.01); G06N 5/003 (2013.01); G06N 20/20 (2019.01); G06Q 10/1053 (2013.01); H04L 67/306 (2013.01); G06N 3/0481 (2013.01); G06Q 50/01 (2013.01);
Abstract

In an example, features in a boosting decision tree model are initialized to zero, the boosting decision tree model located in a GLMM and connected to a deep neural network collaborative filtering model via a prediction layer. While the features in the boosting decision tree model remain zero, the deep neural network collaborative filtering model is trained. One or more trees in the boosting decision tree model are boosted using logits produced by the training of the deep neural network collaborative filtering model as a margin. The prediction layer is trained using features from the deep neural network collaborative filtering model and features from the boosting decision tree model. It is then determined whether a set of convergence criteria is met. If not, then the deep neural network collaborative filtering model is retrained using the features and the process is repeated until the set of convergence criteria is met.


Find Patent Forward Citations

Loading…