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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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