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

Neural network convolution calculation acceleration method based on Kmeans algorithm

A kmeans clustering and neural network technology, applied in biological neural network models, computing, neural architecture, etc., to accelerate processing, reduce multiplication operations, and reduce multiplication calculations.

Pending Publication Date: 2020-02-18
NAT UNIV OF DEFENSE TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods have certain limitations, that is, they are not applicable to all networks

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 convolution calculation acceleration method based on Kmeans algorithm
  • Neural network convolution calculation acceleration method based on Kmeans algorithm
  • Neural network convolution calculation acceleration method based on Kmeans algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0021] The neural network convolution calculation acceleration method based on the Kmeans algorithm of the present invention is mainly through the traditional network structure (such as figure 1 ) to add a Kmeans layer to reduce the operation of the convolutional layer. Because in the operation process of the convolutional layer, the weight data will be reused many times after being taken out, and the cycle of fetching the data is much shorter than the cycle of processing the weight. If you want to increase the processing speed of the entire network, you should start by reducing the processing time of the convolutional layer.

[0022] The processing of the convolutional layer is mainly a multiplication and accumulation operation. The input data after passing through the Kmeans layer is aggregated into a fixed k class. It is only nece...

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 discloses a neural network convolution calculation acceleration method based on a Kmeans algorithm, and the method comprises the steps: adding a Kmeans clustering layer in neural networkconvolution, and enabling input data passing through the Kmeans clustering layer to be clustered into fixed k types; and calculating the multiplication of the k types of data and the convolution kernel in the convolution layer, making the result into a lookup table, and searching and obtaining the result of the multiplication of all the original input data and the convolution kernel through the lookup table. The method has the advantages that the implementation method is simple, multiplication operation of the convolutional layer of the neural network can be effectively reduced, and the like.

Description

technical field [0001] The present invention mainly relates to the technical field of convolutional neural networks, in particular to a neural network convolution calculation acceleration method based on the Kmeans algorithm Background technique [0002] From the end of the first decade of the 21st century, with the rise of big data and the continuous improvement of computing power, the research of machine learning has begun to pick up. Among them, the deep learning technology represented by artificial neural network has developed rapidly and has been widely used. into many applications of artificial intelligence, including image recognition, natural language processing, and robotics. [0003] In the past, the implementation platform for neural networks was mainly general-purpose processors, especially the image processing unit (GPU), which is the mainstream choice for DNN acceleration. But as neural networks become more widely used, the networks themselves become more comp...

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): G06K9/62G06N3/04
CPCG06N3/045G06F18/23213
Inventor 郭阳陈桂林马胜徐睿李艺煌王耀华
Owner NAT UNIV OF DEFENSE TECH
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