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

Method and device for realizing Bayesian neural network by using memristor intrinsic noise

A Bayesian network and neural network technology, which is applied in the field of realizing Bayesian neural network using memristor intrinsic noise, can solve problems such as high computing cost, and achieve the effect of low power consumption and high speed

Active Publication Date: 2020-04-03
TSINGHUA UNIV
View PDF7 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This usually comes at a high computational cost and is a major limitation in the application of Bayesian neural 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
  • Method and device for realizing Bayesian neural network by using memristor intrinsic noise
  • Method and device for realizing Bayesian neural network by using memristor intrinsic noise
  • Method and device for realizing Bayesian neural network by using memristor intrinsic noise

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049]Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0050] A method and device for implementing a Bayesian neural network by using the intrinsic noise of a memristor according to an embodiment of the present invention will be described below with reference to the accompanying drawings.

[0051] Firstly, a method for implementing a Bayesian neural network by utilizing the intrinsic noise of a memristor according to an embodiment of the present invention will be described with reference to the accompanying drawings.

[0052] figure 2 It is a flow chart of a method for implementing ...

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 method and device for realizing a Bayesian neural network by using memristor intrinsic noise. The method comprises the steps: obtaining a Bayesian network, and carrying out the training of the Bayesian network according to a selected data set, and obtaining the weight distribution of the Bayesian network; and processing the weight distribution of the Bayesian network, calculating according to the processed weight distribution and the conductivities of the plurality of memristors to obtain a target conductivity value, and mapping the target conductivity value into thememristors. According to the method, the Bayesian neural network is realized by utilizing the memristor cross array, and the power consumption is low, and the calculation speed is high, and the calculation energy efficiency is high.

Description

technical field [0001] The invention relates to the technical field of neural networks, in particular to a method and device for realizing a Bayesian neural network by utilizing the intrinsic noise of a memristor. Background technique [0002] In the field of artificial intelligence, deep neural networks (DNNs) have developed rapidly in recent years, and have achieved remarkable results in image and visual computing, speech and language processing, information security, chess games and other fields. However, normal DNNs are difficult to defend against attacks, such as in the case of image classification, where small perturbations imperceptible to human eyes are added to the input image, but DNNs produce erroneous and overconfident classification results because DNNs cannot capture predictions and Uncertainty. Such perturbed inputs (known as adversarial examples) are a major obstacle to using DNNs in safety-critical applications. On the other hand, Bayesian neural network (...

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): G06N3/04G06N3/08G11C13/00
CPCG06N3/08G11C13/0004G06N3/047
Inventor 吴华强高滨林钰登张清天唐建石钱鹤
Owner TSINGHUA 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

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