Invention Grant
- Patent Title: Slimming of neural networks in machine learning environments
-
Application No.: US16632215Application Date: 2017-08-18
-
Publication No.: US11537892B2Publication Date: 2022-12-27
- Inventor: Shoumeng Yan , Jianguo Li , Zhuang Liu
- Applicant: Intel Corporation
- Applicant Address: US CA Santa Clara
- Assignee: Intel Corporation
- Current Assignee: Intel Corporation
- Current Assignee Address: US CA Santa Clara
- Agency: Jaffery Watson Mendonsa & Hamilton LLP
- International Application: PCT/CN2017/097977 WO 20170818
- International Announcement: WO2019/033380 WO 20190221
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N3/04 ; G06N3/063 ; G06T1/20

Abstract:
A mechanism is described for facilitating slimming of neural networks in machine learning environments. A method of embodiments, as described herein, includes learning a first neural network associated with machine learning processes to be performed by a processor of a computing device, where learning includes analyzing a plurality of channels associated with one or more layers of the first neural network. The method may further include computing a plurality of scaling factors to be associated with the plurality of channels such that each channel is assigned a scaling factor, wherein each scaling factor to indicate relevance of a corresponding channel within the first neural network. The method may further include pruning the first neural network into a second neural network by removing one or more channels of the plurality of channels having low relevance as indicated by one or more scaling factors of the plurality of scaling factors assigned to the one or more channels.
Public/Granted literature
- US20200234130A1 SLIMMING OF NEURAL NETWORKS IN MACHINE LEARNING ENVIRONMENTS Public/Granted day:2020-07-23
Information query