Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method and apparatus for compressing neural network

A neural network and compression layer technology, applied in the computer field, can solve the problems of slow running speed, less available storage space, downtime, etc., and achieve the effect of effective compression

Pending Publication Date: 2019-07-09
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF11 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If the user installs many applications containing neural networks on the device held by the user (such as a smartphone, tablet computer, etc.), the device may have less available storage space and the device may run slowly. , downtime and other abnormal situations

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method and apparatus for compressing neural network
  • A method and apparatus for compressing neural network
  • A method and apparatus for compressing neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain related inventions, rather than to limit the invention. It should also be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

[0031] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.

[0032] figure 1 An exemplary system architecture 100 is shown to which an embodiment of the method for compressing a neural network or the apparatus for compressing a neural network of the present application can be applied.

[0033] Such as figure 1 As shown, system archi...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The embodiment of the invention discloses a method and a device for compressing a neural network. A specific embodiment of the method comprises the steps of obtaining a to-be-compressed trained neuralnetwork; selecting at least one layer from all layers of the neural network as a layer to be compressed; sequentially executing the following processing steps on each layer to be compressed accordingto the descending order of the hierarchy number of the layers to be compressed in the neural network: quantifying parameters in the layers to be compressed based on the appointed number, and trainingthe quantized neural network based on a preset training sample by utilizing a machine learning method; and determining the neural network obtained by performing the processing step on each selected layer to be compressed as a compressed neural network, and storing the compressed neural network. According to the embodiment, effective compression of the neural network is realized.

Description

technical field [0001] The embodiments of the present application relate to the field of computer technology, specifically to the field of Internet technology, and in particular to a method and device for compressing a neural network. Background technique [0002] At present, with the continuous development of artificial intelligence, the scope of application of neural networks is also expanding. Here, the neural network is an abbreviation for artificial neural network. Neural networks can be applied to the server to process images, text, audio, etc. Of course, neural networks can now also be included in client applications. Users can edit images, text, audio, etc. through the neural network in the client application installed on their terminal equipment. [0003] Existing neural networks usually occupy a lot of storage space, such as disk space or memory space. If the user installs many applications containing neural networks on the device held by the user (such as a sm...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06N3/08
CPCG06N3/082G06N3/08G06N3/063G06N3/044G06N3/045G06N3/10G06N3/04
Inventor 张刚
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com