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

Layering quantization method and device for complex neural network

A neural network and artificial neural network technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve problems such as inapplicability

Active Publication Date: 2018-02-13
XILINX INC
View PDF2 Cites 49 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above scheme is not suitable for popular networks (GoogLeNet, SqueezeNet, etc.)

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
  • Layering quantization method and device for complex neural network
  • Layering quantization method and device for complex neural network
  • Layering quantization method and device for complex neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] Part of the content of this application has been published in the academic article "Going Deeper With Embedded FPGA Platform for Convolutional Neural Network" (2016.2) by the inventor Yao Song. This application contains the content of the above-mentioned article, and has made more improvements on the basis of it.

[0027] In this application, image processing will be mainly used as an example to illustrate the improvement of CNN by the present invention. 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 is an example of CNN

[0028] Basic concepts of CNN

[0029] CNN achieves the most advanced performance in a wide range of visual related tasks. To help understand the CNN-based image classification algorithm analyzed in this application, we first introduce the basic knowledge of CNN, introduce the image network dat...

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 an artificial neural network (ANN), for example, a convolutional neural network (CNN), in particular to how to achieve compression and acceleration of the ANN through fixed-point quantization of a complex neural network.

Description

[0001] Cited priority application [0002] This application claims the priority of the Chinese patent application 201610663201.9, "A Method for Optimizing Artificial Neural Networks" and the Chinese Patent Application 201610663563.8 "A Deep Processing Unit Used to Realize ANN". Technical field [0003] The present invention relates to artificial neural networks (ANN), such as convolutional neural networks (CNN), and in particular to how to realize compression and acceleration of artificial neural networks through fixed-point quantization of complex neural networks. Background technique [0004] Methods based on artificial neural networks, especially Convolutional Neural Networks (CNN, Convolutional Neural Network) have achieved great success in many applications, especially in the field of computer vision has been the most powerful and widely used. [0005] Image classification is a basic problem in computer vision (CV). Convolutional Neural Network (CNN) has made great progress in i...

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): G06N3/08G06K9/62
CPCG06N3/084G06F18/241
Inventor 余金城姚颂
Owner XILINX INC
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