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

A kind of convolutional neural network binarization method and operation circuit

A convolutional neural network and computing circuit technology, applied in the field of convolutional neural network binarization methods and computing units, can solve problems such as low computing efficiency and slow speed, achieve fast computing speed, reduce hardware complexity, and save computing resource effect

Active Publication Date: 2022-07-26
BEIHANG UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] This application proposes a convolutional neural network binarization method and an operation circuit, which solves the problems of low operation efficiency and slow speed in the prior art

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
  • A kind of convolutional neural network binarization method and operation circuit
  • A kind of convolutional neural network binarization method and operation circuit
  • A kind of convolutional neural network binarization method and operation circuit

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below with reference to the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0026] The technical solutions provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0027] figure 1 Diagram of the binarization method for convolutional neural network.

[0028] An embodiment of the present application provides a method for binari...

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 present application discloses a convolutional neural network binarization method and an operation circuit, which solve the problems of low operation efficiency and slow speed in the prior art. A convolutional neural network binarization method, which convolves the convolution kernel and feature map through an AND gate. Accumulate the results of the convolution operation. Normalize the data accumulated by the convolution operation to be between (‑1, +1). The normalized result is binarized into 1 and 0, and the binarized result is kept or inverted. Perform a pooling operation on the maintained or negated result, and output the result of the operation. The invention also provides a convolutional neural network binarization operation circuit based on the binarization method. By using an AND gate to replace the original multiplier and XNOR gate, not only the resource consumption is less, but the calculation speed is also higher. quick.

Description

technical field [0001] The invention relates to a convolutional neural network circuit, in particular to a convolutional neural network binarization method and an arithmetic unit. Background technique [0002] Convolutional Neural Networks have been continuously developed and have applications in various applications such as image recognition, natural language processing, speech recognition, etc. Convolutional neural networks usually contain a large number of parameters and require a lot of computation, which limits their application in the field of edge computing. The binary neural network is obtained by binarizing the ordinary convolutional neural convolution kernel, input data, and activation value. The method for binarizing a convolutional neural network in the prior art: the data greater than or equal to 0 is quantized as +1, and the data less than 0 is quantized as -1. Corresponding to this binarization method, the XNOR operation can be used to replace the multiplier...

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 Patents(China)
IPC IPC(8): G06N3/04G06N3/063
CPCG06N3/063G06N3/045
Inventor 李洪革冼章孔
Owner BEIHANG UNIV
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