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

Structural learning and simplification method of deep neural network

A technology of deep neural network and neural network model, which is applied in the field of structure learning and simplification of deep neural network, and can solve problems such as increasing hardware resources.

Pending Publication Date: 2022-05-13
ELECTRONICS & TELECOMM RES INST
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] This increase in the amount of computation and memory results in an increase in hardware resources

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
  • Structural learning and simplification method of deep neural network
  • Structural learning and simplification method of deep neural network
  • Structural learning and simplification method of deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] These and other objects, advantages and features of the present invention and methods of achieving them will be clarified by the following embodiments described with reference to the accompanying drawings.

[0033] However, this invention may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will fully convey the purpose, configuration and effects of the present invention to those skilled in the art. The scope of the invention is limited only by the appended claims.

[0034] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms "a" and "an" include plural forms unless the context clearly dictates otherwise. When used in this specification, the terms "comprising" and / or "comprising" specify the presence of stated elements, steps, ...

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 invention relates to a deep neural network structure learning and simplifying method. A structure learning and simplification method of a deep neural network according to an embodiment of the present invention comprises the steps of: (a) generating parameters of a neural network model; (b) generating a target function corresponding to a neural network model based on the parameters; and (c) learning the model while performing training on the parameters based on the learning data and the objective function.

Description

technical field [0001] The invention relates to a method for structure learning and model compression of a deep neural network. Background technique [0002] Deep Neural Networks (often abbreviated as DNN) are widely used in various fields such as computer processing, speech recognition, and image recognition. [0003] With the development of technologies related to deep neural networks, deep neural networks have become larger and more complex, and thus the amount of computation and memory used to drive deep neural networks is rapidly increasing. [0004] This increase in the amount of computation and memory results in an increase in hardware resources. [0005] In addition, deep neural networks can relieve the burden of feature engineering by human experts, however, much effort by human experts is required to design effective structures for deep neural networks. Contents of the invention [0006] technical problem [0007] The present invention is proposed to solve the...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/082G06N3/045G06N3/063G06N3/084G06N3/048G06N3/0495G06N3/0464G06N3/09G06N3/0985G06N3/04G06N3/08
Inventor 李容真
Owner ELECTRONICS & TELECOMM RES INST
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