Neural network three-body model based on mesoscopic system

A neural network and volume model technology, applied in biological neural network models, neural architecture, character and pattern recognition, etc., can solve problems such as inability to directly apply data, irregularity and unstructured

Pending Publication Date: 2021-11-02
CHANGCHUN UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the irregularity, unstructured, and disordered characteristics of laser point clouds, traditional Convolutional Neural Networks (CNN) cannot be directly applied to such 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
  • Neural network three-body model based on mesoscopic system
  • Neural network three-body model based on mesoscopic system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0023] as attached figure 1 As shown, the present invention provides a kind of neural network three-body model based on mesoscopic system, including in this neural network three-body model:

[0024] Learning body, mainly used for the construction from raw data to high-level mesoscopic system;

[0025] Memory, mainly used to store and reorganize neuron attribute information in different mesoscopic systems;

[0026] The interpretation body is mainly used as the reverse propagation process of the learning body, and then realizes the corresponding explanation function of the high-level mesoscopic system for the low-level mesoscopic system.

[0027] as attached figure 2 As shown, the steps of this method are:

[0028] (1) In order to build a split neural network collaborative computing model, it is necessary to split and reorganize the single learning body of the traditional neural network, especially to store important node information in memory, so as to provide a strong guar...

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 provides a neural network three-body model based on mesoscopic systems. The neural network three-body model comprises a learning body which is mainly used for construction from original data to a high-level mesoscopic system; a memory body which is mainly used for storing and recombining neuron attribute information in the different mesoscopic systems; and an interpretation body which is mainly used as a reverse propagation process of the learning body so as to realize a corresponding interpretation function of the high-level mesoscopic system to a low-level mesoscopic system. According to the invention, important nodes and intrinsic information in a deep learning process are stored by constructing the three-body neural network model based on the mesoscopic systems, and a memory organization structure is further formed, so that important basis and guarantee are provided for interpretability of deep learning, and a new direction is provided for the development of a brand new neural network which better conforms to a human learning cognition mode.

Description

technical field [0001] The invention belongs to the field of neural network three-body models, in particular to a neural network three-body model based on a mesoscopic system. Background technique [0002] In recent years, in many fields such as industrial inspection and intelligent body operation, the demand for large-scene laser three-dimensional (Three Dimensional, 3D) point cloud target recognition and tracking technology based on deep learning has become increasingly strong. However, due to the irregularity, unstructured, and disordered characteristics of laser point clouds, traditional convolutional neural networks (CNN) cannot be directly applied to such data. [0003] Therefore, in order to meet the needs of complex systems, a mesoscopic system-based neural network three-body model is proposed to store important nodes and intrinsic information in the deep learning process, and then form a memory organization structure, which is an interpretable model for deep learnin...

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): G06K9/00G06N3/04
CPCG06N3/045
Inventor 胡奇王春阳段锦翟朗田嘉政
Owner CHANGCHUN UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products