Title:
METHOD AND DEVICE FOR OPTIMIZING NEURAL NETWORK
Document Type and Number:
WIPO Patent Application WO/2018/068421
Kind Code:
A1
Abstract:
Disclosed are a method and device for optimizing a neural network. The method comprises: obtaining an initial neural network meeting a set precision condition, and determining a weight parameter matrix between two adjacent layers of unit nodes in the initial neural network; processing the weight parameter matrix according to a set deletion threshold and determining a unit node to be deleted in the initial neural network; and deleting the unit node to form an optimized target neural network. The method can easily and efficiently compress a neural network, thereby implementing the optimization of the neural network. Therefore, during human face recognition based on an optimized neural network, the recognition processing speed can be increased, the recognition processing time can be shortened, and the occupation of spaces, such as storage, a running memory, and a display memory, can be reduced.
Inventors:
ZHANG YUBING (CN)
Application Number:
PCT/CN2016/113271
Publication Date:
April 19, 2018
Filing Date:
December 29, 2016
Export Citation:
Assignee:
GUANGZHOU SHIYUAN ELECTRONICS CO LTD (CN)
International Classes:
G06N3/08
Foreign References:
| CN104751228A | 2015-07-01 | |||
| CN105373830A | 2016-03-02 | |||
| CN105160396A | 2015-12-16 | |||
| CN104504442A | 2015-04-08 | |||
| US20100017351A1 | 2010-01-21 |
Attorney, Agent or Firm:
BEYOND ATTORNEYS AT LAW (CN)
Download PDF:
Previous Patent: IMAGE PROCESSING METHOD AND APPARATUS
Next Patent: METHOD AND SYSTEM FOR IMPROVING KITCHEN VENTILATOR VOICE RECOGNITION RATE
Next Patent: METHOD AND SYSTEM FOR IMPROVING KITCHEN VENTILATOR VOICE RECOGNITION RATE