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

Method for constructing neural network model of super deep adversarial learning

A neural network model and deep technology, applied in biological neural network models, neural learning methods, neural architectures, etc., can solve problems such as unpredictability and uncertainty of processing results, and achieve high processing efficiency and clear goals.

Pending Publication Date: 2018-09-07
顾泽苍
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0033] What is artificial intelligence? Simply speaking, it is to use computers to realize the functions of human brains, that is, to realize the effects of human brain thinking through computers. The problems to be solved are often uncertain, or unpredictable in advance.

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 for constructing neural network model of super deep adversarial learning
  • Method for constructing neural network model of super deep adversarial learning
  • Method for constructing neural network model of super deep adversarial learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0190] The embodiments of the present invention will be further described below in conjunction with the accompanying drawings, but the embodiments of the present invention are illustrative rather than limiting.

[0191] figure 1 is a schematic diagram of multiple probability scales defined for probability distributions.

[0192] Such as figure 1 As shown: Assuming a probability distribution 101 in the probability space, there must be a multi-probability scale, which can represent the probability distribution status of the complex position of the probability distribution. Here, when the center value of the probability distribution in a certain area is 102, it can be set The first scale value is 103, which corresponds to a probability distribution value of 106 in the area. The second scale value can be set to 104, which corresponds to a probability distribution value of 107 in the area. The third scale value can be set to 105. Corresponding to the probability distribution valu...

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 relates to a method for constructing a neural network model of super deep adversarial learning in the field of artificial intelligence. According to the invention, adversarial learning is unsupervised machine learning which is directly for small data and transfers towards a high probability direction in a self-disciplined manner on the basis of a multi-probability scale, a strict distance relationship of data traversing different spaces is obtained through learning, a fuzzy event probability measure theory is introduced, the microscopic fuzzy information and the probability information are fully utilized, and the most rigorous adversarial relationship for performing adversity between the data is further established, so that the best adversarial learning effect can be obtained. The implementation effects are that problems of the optimal classification with the maximum probability and highest reliability, optimal pattern recognition and optimal prediction of the data traversing different spaces can be solved, a real simulated brain neuron mechanism can be realized, and an optimal algorithm of machine learning is achieved, thereby being an epoch-making new model capableof enabling the artificial intelligence to be widely applied in industry.

Description

【Technical field】 [0001] The invention belongs to a method for forming a neural network model of ultra-deep confrontation learning in the field of artificial intelligence. 【Background technique】 [0002] With the brilliant record of AlphaGo invested and developed by Google in defeating all human chess players, it has once again set off an upsurge of pursuing deep learning all over the world. The number of patent applications related to artificial intelligence in the past year has almost exceeded the total number of patents related to artificial intelligence in all previous years. [0003] In this regard, the famous Japanese Furukawa Electromechanical Company published a patent application for "Image Processing Method and Image Processing Device" (Patent Document 1). Extract the outline of the image. [0004] In the application of automatic driving of automobiles, the famous Japanese Toyota Corporation published the patent of "Driving Direction Estimation Device" (Patent Do...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08G06V10/776
CPCG06N3/088G06N3/047G06N3/045G06V10/82G06V10/776G06V10/7715G06N3/043G06F18/2137G06F18/217
Inventor 顾泽苍
Owner 顾泽苍
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