Global pooling method of neural network and many-core system

A neural network and pooling technology, applied in the field of neural networks, can solve problems such as long calculation delays, and achieve the effect of reducing storage and calculation delays

Pending Publication Date: 2021-03-05
LYNXI TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in related technologies, the calculat

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
  • Global pooling method of neural network and many-core system
  • Global pooling method of neural network and many-core system
  • Global pooling method of neural network and many-core system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0071] figure 1 It shows a schematic diagram of general pooling of CNN neural network, see figure 1 It can be seen that in the traditional pooling process, the feature map will be slid in the form of a window (similar to the window sliding of the convolution). The operation is to take the average or maximum value in the window as the result. After the operation, the feature map is down-sampled. Reduced overfitting.

[0072] On th...

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 global pooling method of a neural network and a many-core system. The method comprises the steps of receiving point data of to-be-processed data input by a previous network layer in sequence; and after each piece of point data is received, executing a preset pooling operation based on the currently received point data until pooling of all point data of the to-be-processeddata is completed. Based on the scheme provided by the invention, the point operation can be used for replacing the graph operation under the line pipeline operation of the many-core system, that is,after each point data is received, the point data is processed once to obtain the intermediate pooling result until the final pooling result of the to-be-processed data is finally obtained, so that the calculation delay is reduced.

Description

technical field [0001] The present disclosure relates to the technical field of neural networks, in particular to a global pooling method of neural networks and a many-core system. Background technique [0002] With the continuous development of artificial intelligence technology, the application of deep learning is becoming more and more extensive. Convolutional Neural Networks (CNN) is a type of Feedforward Neural Networks (Feedforward Neural Networks) that includes convolution calculations and has a deep structure, and is one of the representative algorithms for deep learning. The last layer of a traditional CNN is a fully connected layer with a large number of parameters, which can easily cause overfitting (such as Alexnet). In a CNN model, most of the parameters are occupied by the fully connected layer, which affects the processing speed. Increased processing time. Therefore, a global mean pooling scheme is proposed to replace the fully connected layer. However, in ...

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
IPC IPC(8): G06N3/04G06N3/063G06N3/08
CPCG06N3/063G06N3/08G06N3/045G06N3/10
Inventor 戚海涛李涵
Owner LYNXI 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