Title:
NEURAL NETWORK CONVOLUTION COMPUTATION METHOD AND DEVICE, AND COMPUTER-READABLE STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2018/107383
Kind Code:
A1
Abstract:
A neural network convolution computation method and device, used for achieving convolution computation of a weight matrix and neurons in a neural network in a matrix multiplication manner. The method comprises: first performing winograd transform on a neuron matrix and a weight matrix to obtain a transformed neuron matrix and a transformed weight matrix (step 1); then performing a matrix multiplication operation on the transformed neuron matrix and the transformed weight matrix to obtain a multiplication matrix (step 2); and finally performing winograd inverse transform on the multiplication matrix to obtain the computation result (step 3).
Inventors:
CHEN YUNJI (CN)
ZHUANG YIMIN (CN)
LIU SHAOLI (CN)
GUO QI (CN)
CHEN TIANSHI (CN)
ZHUANG YIMIN (CN)
LIU SHAOLI (CN)
GUO QI (CN)
CHEN TIANSHI (CN)
Application Number:
PCT/CN2016/109862
Publication Date:
June 21, 2018
Filing Date:
December 14, 2016
Export Citation:
Assignee:
SHANGHAI CAMBRICON INF TECH CO LTD (CN)
International Classes:
G06F15/16
Foreign References:
CN104915322A | 2015-09-16 | |||
CN106203617A | 2016-12-07 | |||
CN106127297A | 2016-11-16 | |||
CN101893686A | 2010-11-24 |
Other References:
TAN, FUPING ET AL.: "A New Scheme to Divide Odd-sized Matrices for the Winograd's Algorithm", COMMUNICATION ON APPLIED MATHEMATICS AND COMPUTATION, vol. 18, no. 1, 30 June 2004 (2004-06-30)
Attorney, Agent or Firm:
CHINA SCIENCE PATENT & TRADEMARK AGENT LTD. (CN)
Download PDF: