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

Method and device for adjusting artificial neural network

An artificial neural network and neural network model technology, applied in the field of fixed-point quantification of neural networks, can solve the problems of only considering the deployment stage and ignoring the training stage, and achieve the effect of avoiding convergence and oscillation problems and ensuring accuracy.

Active Publication Date: 2019-12-10
XILINX TECH BEIJING LTD
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing quantization methods usually only consider the deployment phase and ignore the training phase, or pursue accuracy but cannot overcome the limitations of hardware.

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
  • Method and device for adjusting artificial neural network
  • Method and device for adjusting artificial neural network
  • Method and device for adjusting artificial neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Hereinafter, preferred embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although the drawings show preferred embodiments of the present disclosure, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0033] The solution of this application is applicable to various artificial neural networks, including deep neural networks (DNN), recurrent neural networks (RNN) and convolutional neural networks (CNN). The following takes CNN as an example for a certain degree of background explanation.

[0034] Basic concepts of CNN

[0035] CNN achieves the most advanced performance in a wide range of visual related tasks. To help under...

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

A method and a device for adjusting an artificial neural network (ANN) are provided. The ANN at least comprises a plurality of layers, and the method comprises the steps: obtaining a to-be-trained neural network model; training the neural network model by using high-bit fixed-point quantization to obtain a trained high-bit fixed-point quantization neural network model; carrying out fine tuning onthe high-bit fixed-point quantization neural network model by using low bits to obtain a trained neural network model with low-bit fixed-point quantization; and outputting the trained neural network model with low-bit fixed-point quantization. According to the neural network training scheme with the bit width gradually reduced, the training and deployment of the neural network are considered, so that the calculation precision comparable to that of a floating point network can be realized under the condition of extremely low bit width.

Description

Technical field [0001] The present invention relates to artificial neural networks (ANN), such as convolutional neural networks (CNN), and in particular to fixed-point quantization of neural networks. Background technique [0002] Methods based on artificial neural networks (ANN, Artificial Neural Network), especially convolutional neural networks (CNN, Convolutional Neural Network) have achieved great success in many applications. In the field of computer vision, especially for image classification, the introduction of CNN has greatly improved the accuracy of image classification. [0003] Although the CNN-based method has advanced performance, it requires more computing and memory resources than traditional methods. Especially with the development of neural networks, large-scale neural networks have more and more levels and data volume, which brings huge challenges to the deployment of neural networks. Although most CNN-based methods need to rely on large-scale servers, in rece...

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
CPCG06N3/08G06N3/045
Inventor 高梓桁
Owner XILINX TECH BEIJING 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