Invention Grant
- Patent Title: Template regularization for generalization of learning systems
- Patent Title (中): 学习系统泛化的模板正则化
-
Application No.: US14142970Application Date: 2013-12-30
-
Publication No.: US09390382B2Publication Date: 2016-07-12
- Inventor: Yoram Singer , Tal Shaked , Tushar Deepak Chandra , Tze Way Eugene Ie , James Vincent McFadden , Jeremiah Harmsen , Kristen Riedt LeFevre
- Applicant: Google Inc.
- Applicant Address: US CA Mountain View
- Assignee: Google Inc.
- Current Assignee: Google Inc.
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- Main IPC: G06N99/00
- IPC: G06N99/00

Abstract:
Systems and techniques are disclosed for training a machine learning model based on one or more regularization penalties associated with one or more features. A template having a lower regularization penalty may be given preference over a template having a higher regularization penalty. A regularization penalty may be determined based on domain knowledge. A restrictive regularization penalty may be assigned to a template based on determining that a template occurrence is below a stability threshold and may be modified if the template occurrence meets or exceeds the stability threshold.
Public/Granted literature
- US20150186794A1 TEMPLATE REGULARIZATION FOR GENERALIZATION OF LEARNING SYSTEMS Public/Granted day:2015-07-02
Information query