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

Image classification method based on random calculation Bayesian neural network error injection

A neural network and random computing technology, applied in the field of image processing, to achieve good image classification effect, reduce resource occupation and hardware overhead

Active Publication Date: 2021-10-19
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem of image classification, and propose an image classification method based on random calculation Bayesian neural network error injection

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
  • Image classification method based on random calculation Bayesian neural network error injection
  • Image classification method based on random calculation Bayesian neural network error injection
  • Image classification method based on random calculation Bayesian neural network error injection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] Embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0043] Such as figure 1 As shown, the present invention provides a kind of image classification method based on stochastic calculation Bayesian neural network error injection, comprising the following steps:

[0044] S1: Collect the image data set as the input data of the Bayesian neural network, collect the weight parameters and bias parameters obtained from the training of the Bayesian neural network, and use the input data, weight parameters and bias of the Bayesian neural network in floating-point form parameters to scale;

[0045]S2: Use a linear feedback shift register and a comparator to form a forward conversion circuit, and convert the scaled floating-point input data, floating-point weight parameters and floating-point bias parameters into a random bit stream form through the forward conversion circuit, Obtain input data bit stream, weight pa...

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 an image classification method based on random calculation Bayesian neural network error injection. The method comprises the following steps: S1, scaling input data, weight parameters and bias parameters; S2, converting the scaled floating point input data, the scaled floating point weight parameter and the scaled floating point bias parameter into a random bit stream form through a forward conversion circuit; S3, building a random calculation neuron structure of the Bayesian neural network; S4, calculating the scaling of each neuron node, and performing forward reasoning; S5, converting the output bit stream into a floating point form, and obtaining an output result of single reasoning; and S6, repeating the steps S4-S5, taking a mean value, and taking the mean value as a classification result. According to the image classification method based on Bayesian neural network error injection, inherent noise characteristics are calculated randomly, an additional error injection circuit does not need to be introduced, and unification of calculation and error injection in the Bayesian neural network reasoning process is achieved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image classification method based on random calculation Bayesian neural network error injection. Background technique [0002] The weights and thresholds of Bayesian Neural Networks (BNNs) are expressed in the form of random distribution, which is a random number subject to the posterior random distribution, that is, the Bayesian inference algorithm is introduced into the neural network model. The essence of its algorithm lies in: repeating the forward propagation with different random sampling parameters to determine the final output. Considering the implementation at the hardware level, additional error generation circuits are required to inject errors to satisfy the prediction distribution that conforms to the randomness of each calculation of the network. This is a huge challenge for traditional CMOS circuits. [0003] For the hardware implementation...

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): G06K9/62G06N3/04G06N3/08G06N5/04G06K9/00G06N3/063
CPCG06N3/08G06N5/046G06N3/063G06N3/042G06N3/047G06N3/045G06F18/24155G06F18/29Y02D10/00
Inventor 姜书艳孙召曦许怡楠黄乐天
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
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