Neural network architecture searching method and device, equipment and medium

A neural network and architecture technology, applied in neural architecture, neural learning methods, biological neural network models, etc., can solve problems such as difficulty in meeting business needs and low search efficiency

Pending Publication Date: 2021-09-07
HUAWEI CLOUD COMPUTING TECH CO LTD
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] This application provides a neural network architecture search method, which solves the problem of search efficiency in related technologies by decoupling the training process of different initial sub-models, and decoupling the neural network architecture search process and the initial sub-model training process. Low, difficult to meet business needs

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
  • Neural network architecture searching method and device, equipment and medium
  • Neural network architecture searching method and device, equipment and medium
  • Neural network architecture searching method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] The solutions in the embodiments provided in the present application will be described below with reference to the drawings in the present application.

[0071] The terms "first", "second" and the like in the specification and claims of the present application and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, and this is merely a description of the manner in which objects with the same attribute are described in the embodiments of the present application.

[0072] In order to facilitate the understanding of the technical solution of the present application, some technical terms involved in the present application are introduced below.

[0073] A neural network (NN) is a neural network that simulates the human brain in order to achieve a mathematical model similar to artificial...

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 provides a neural network architecture search method, which is applied to a search system, the search system comprises a generator and a searcher. The method comprises the following steps: the generator generates a plurality of neural network architectures according to a search space, and the searcher obtains evaluation index values of a plurality of sub-models on first hardware obtained according to the plurality of neural network architectures, and the searcher determines a first target neural network architecture meeting a preset condition according to the neural network architecture corresponding to the plurality of sub-models and the evaluation index values of the plurality of sub-models on the first hardware. Therefore, decoupling of different initial sub-model training processes and decoupling of a neural network architecture search process and the initial sub-model training process are realized, the search duration is shortened, and the search efficiency is improved.

Description

[0001] This application claims the priority of the Chinese patent application with the application number 202010148339.1 and the application title "A Method and System for Neural Network Architecture Search" filed with the China Intellectual Property Office on March 5, 2020, the entire contents of which are incorporated by reference in this application. technical field [0002] The present application relates to the technical field of artificial intelligence, and in particular to a neural network architecture search method, device, device, and computer-readable storage medium. Background technique [0003] With the rise of artificial intelligence (AI) technology, especially the rise of neural networks (neural networks), great progress has been made in many fields such as image processing, audio and video recognition, and the like. At present, the effect of AI-based image processing or audio and video recognition often depends on the performance of the neural network used. A...

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
CPCG06N3/049G06N3/08G06N3/045G06N3/0985G06N3/0442G06N3/082G06N3/098G06N3/04
Inventor 周卫民郭益君李亿麦宇庭邓彬彬
Owner HUAWEI CLOUD COMPUTING TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap