Invention Grant
- Patent Title: Fixed point neural network based on floating point neural network quantization
-
Application No.: US14920099Application Date: 2015-10-22
-
Publication No.: US10373050B2Publication Date: 2019-08-06
- Inventor: Dexu Lin , Venkata Sreekanta Reddy Annapureddy , David Edward Howard , David Jonathan Julian , Somdeb Majumdar , William Richard Bell, II
- 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 ; G06N3/10 ; G06K9/46 ; G06N3/06
Abstract:
A method of quantizing a floating point machine learning network to obtain a fixed point machine learning network using a quantizer may include selecting at least one moment of an input distribution of the floating point machine learning network. The method may also include determining quantizer parameters for quantizing values of the floating point machine learning network based at least in part on the at least one selected moment of the input distribution of the floating point machine learning network to obtain corresponding values of the fixed point machine learning network.
Public/Granted literature
- US20160328646A1 FIXED POINT NEURAL NETWORK BASED ON FLOATING POINT NEURAL NETWORK QUANTIZATION Public/Granted day:2016-11-10
Information query
