Invention Grant
- Patent Title: Model compression and fine-tuning
-
Application No.: US14846579Application Date: 2015-09-04
-
Publication No.: US10223635B2Publication Date: 2019-03-05
- Inventor: Venkata Sreekanta Reddy Annapureddy , Daniel Hendricus Franciscus Dijkman , David Jonathan Julian
- Applicant: QUALCOMM Incorporated
- Applicant Address: US CA San Diego
- Assignee: QUALCOMM Incorporated
- Current Assignee: QUALCOMM Incorporated
- Current Assignee Address: US CA San Diego
- Agency: Seyfarth Shaw LLP
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N3/04
Abstract:
Compressing a machine learning network, such as a neural network, includes replacing one layer in the neural network with compressed layers to produce the compressed network. The compressed network may be fine-tuned by updating weight values in the compressed layer(s).
Public/Granted literature
- US20160217369A1 MODEL COMPRESSION AND FINE-TUNING Public/Granted day:2016-07-28
Information query
