Invention Grant
- Patent Title: Factorized models
-
Application No.: US14820751Application Date: 2015-08-07
-
Publication No.: US10102482B2Publication Date: 2018-10-16
- Inventor: Heng-Tze Cheng , Jeremiah Harmsen , Alexandre Tachard Passos , David Edgar Lluncor , Shahar Jamshy , Tal Shaked , Tushar Deepak Chandra
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- Main IPC: G06N99/00
- IPC: G06N99/00 ; G06F17/30 ; G06N5/04

Abstract:
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a factorization model to learning features of model inputs of a trained model such that the factorization model is predictive of outcome for which the machine learned model is trained.
Public/Granted literature
- US20170039483A1 FACTORIZED MODELS Public/Granted day:2017-02-09
Information query