Depth learning model matrix compression method and device

A technology of deep learning and compression methods, applied in the computer field, can solve the problems of reducing the amount of calculation, large amount of calculation, and no consideration

Inactive Publication Date: 2015-12-23
HANGZHOU LANGHE TECH
View PDF1 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the model compression method based on SVD matrix decomposition technology treats these elements close to 0 and elements with strong feedback relationship in a similar way, and the amount of calculation is still very large
In addition, the model compression method based on SVD matrix decomposition technology does not consider how to choose K to optimize the operation results and reduce the amount of operation

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
  • Depth learning model matrix compression method and device
  • Depth learning model matrix compression method and device
  • Depth learning model matrix compression method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The principle and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are given only to enable those skilled in the art to better understand and implement the present invention, rather than to limit the scope of the present invention in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0029] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, device, method or computer program product. Therefore, the present disclosure may be embodied in the form of complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0030] According to an embodiment of the present invention, a matrix compression method an...

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 depth learning model matrix compression method and device. The last linear layer of a depth learning model is connected with M hidden nodes and N classification nodes. The last linear layer is corresponding to a weight matrix W. The method comprises the steps that S101 according to the absolute values of the elements of the weight matrix W, a K value is calculated; and Step S102 the last linear layer is divided into a first linear layer and a second linear layer, wherein the weight matrix of the first linear layer is a matrix P of M*K, and the weight matrix of the second linear layer is a matrix Q of K*N. The output of the first linear layer is the input of the second linear layer. M*N is greater than K*(M+N), and the weight matrix W is compressed.

Description

technical field [0001] Embodiments of the present invention relate to the field of computers, and more specifically, embodiments of the present invention relate to a matrix compression method and device for deep learning models. Background technique [0002] This section is intended to provide a background or context for implementations of the invention that are recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section. [0003] The deep learning model is more and more widely used in data analysis. It maps and calculates the data through the linear layer and nonlinear layer between the nodes of different layers, and trains the model during the processing. Correct, update, and ultimately improve classification or prediction accuracy. In deep learning models, usually the last linear layer is the processing layer that connects the hidden nodes to the output classification nodes. Assuming that the number of hidden nodes is M ...

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): G06N3/08
Inventor 陈海波李晓燕
Owner HANGZHOU LANGHE TECH
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