Invention Application
- Patent Title: TRAINING AND OPERATING MULTI-LAYER COMPUTATIONAL MODELS
-
Application No.: US14949156Application Date: 2015-11-23
-
Publication No.: US20170147942A1Publication Date: 2017-05-25
- Inventor: Jianfeng Gao , Li Deng , Xiaodong He , Lin Xiao , Xinying Song , Yelong Shen , Ji He , Jianshu Chen
- Applicant: Microsoft Technology Licensing, LLC
- Main IPC: G06N99/00
- IPC: G06N99/00

Abstract:
A processing unit can successively operate layers of a multilayer computational graph (MCG) according to a forward computational order to determine a topic value associated with a document based at least in part on content values associated with the document. The processing unit can successively determine, according to a reverse computational order, layer-specific deviation values associated with the layers based at least in part on the topic value, the content values, and a characteristic value associated with the document. The processing unit can determine a model adjustment value based at least in part on the layer-specific deviation values. The processing unit can modify at least one parameter associated with the MCG based at least in part on the model adjustment value. The MCG can be operated to provide a result characteristic value associated with test content values of a test document.
Public/Granted literature
- US10445650B2 Training and operating multi-layer computational models Public/Granted day:2019-10-15
Information query