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

Feature extraction method and system applied to deep learning

A technology of feature extraction and deep learning, applied in the direction of instruments, character and pattern recognition, calculation models, etc., to achieve the effect of reducing the amount of calculation and shortening the calculation time

Active Publication Date: 2018-11-13
CHENGDU IDEALSEE TECH
View PDF10 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a feature extraction method and system applied to deep learning, to solve the problem of how to improve the computational efficiency of deep learning in the case of limited computer performance and quantity

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
  • Feature extraction method and system applied to deep learning
  • Feature extraction method and system applied to deep learning
  • Feature extraction method and system applied to deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0027] All the calculations of the existing deep learning are completed by running programs in the computer, that is, the calculations are all software calculations. On the basis of the deep learning of the prior art, the present invention proposes to pass some calculations in the computer calculations through the scheme of the present invention Convert to optical computing to improve the computing efficiency of deep learning. Embodiments of the present invention w...

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 feature extraction method and system applied to deep learning. An existing deep learning calculation mode is improved; in the prior art, for feature extraction in the deep learning, a group of digital signals to be subjected to feature extraction and digital signals of a filter need to be subjected to convolution; the two types of the digital signals are converted into optical signals; at the moment, the optical signals can be simply converted into a frequency domain; the convolution on a time domain is equivalent to the point multiplication on the corresponding frequency domain; the convolution on the time domain is very complex; and the point multiplication operation on the frequency domain can be much simpler. The calculation amount in the deep learning can beeffectively reduced; and after part of the operation is converted into optical calculation, the calculation speed of the part is changed to the optical calculation speed, so that the calculation timeis greatly shortened.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, in particular to a feature extraction method and system applied to deep learning. Background technique [0002] The concept of deep learning originated from the study of artificial neural networks. A multi-layer perceptron with multiple hidden layers is a deep learning structure. Deep learning combines low-level features to form more abstract high-level representation attribute categories or features to discover distributed feature representations of data. Deep learning is a method based on data representation learning in machine learning. In the rapidly developing technological environment, it is increasingly used in machine learning fields such as artificial intelligence, facial recognition, and iris recognition. Human beings are also constantly exploring how to perform feature extraction faster in deep learning. [0003] At present, the convolutional neural network in deep lea...

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): G06K9/00G06N99/00
CPCG06F2218/08
Inventor 周旭东宋海涛闫超
Owner CHENGDU IDEALSEE 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