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

Image tensor data processing method

A processing method and data technology, applied in the field of data processing, can solve problems such as high computational complexity, unsuitable RBM algorithm, and multiple storage space.

Active Publication Date: 2019-07-05
BEIJING UNIV OF TECH
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, more storage space and higher computational complexity are required, which makes the RBM algorithm unsuitable for applications on ordinary devices or high-dimensional data.

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 tensor data processing method
  • Image tensor data processing method
  • Image tensor data processing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0010] This method of image tensor data processing introduces a restricted Boltzmann machine TTRBM model with a tensor train structure. The input and output data of this method are represented by tensors, and the weights of the middle layer are also represented by tensors. Indicates that the restricted weight has the structure of Tensor Train; the number of free parameters in the intermediate layer is controlled by adjusting the rank of tensor Train decomposition; the rank of TT decomposition is adjusted, and different features of the same size are represented.

[0011] The input and output data of the model of the present invention are all represented by tensors, and the weights of the middle layer are also represented by tensors. In order to reduce the number of weights of the middle layer, the weights are restricted to have the structure of Tensor Train in the invention. By adjusting the tensor Train The rank of decomposition controls the number of free parameters in the mid...

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 tensor data processing method which can greatly reduce the number of free parameters in a model, is flexible in weight layer limitation and can be suitable for image tensor data of any order. According to the image tensor data processing method, a restricted Boltzmann machine TTRBM model with a tensor structure is introduced, input data and output data of the method are expressed by tensors, weights of an intermediate layer are also expressed by tensors, and the weights are limited to have the structure of a Trustin. The number of free parameters in an intermediate layer is controlled by adjusting the rank of tensor Train decomposition; the rank of TT decomposition is adjusted, and different feature representations of the same size are adjusted.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a method for processing image tensor data, which can be directly applied to image tensor data of any order. Background technique [0002] Restricted Boltzman Machine (RBM) is a two-layer neural network composed of visible layer and hidden layer. It is widely used in pattern recognition and machine learning because of its strong feature representation ability. The visible layer and hidden layer data in traditional RBM are expressed in vector form. [0003] However, today's real-life data often have high-dimensional properties. In order to apply RBM on these high-dimensional data, the common method is to vectorize the data. The process of vectorization often destroys the internal structure of high-dimensional data, resulting in the loss of important related information, or the problem of dimensionality disaster. In addition, RBM is a fully connected network struct...

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): G06K9/62G06N3/04G06N3/08G06V10/40G06V10/50
CPCG06N3/08G06N3/045G06F18/2133G06V40/169G06V10/40G06V10/50G06V10/82G06N3/047G06F18/29G06N20/10G06F17/18G06T3/4046G06T3/4053
Inventor 孙艳丰句福娇
Owner BEIJING UNIV OF TECH
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