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

Neural network circuit structure capable of changing nerve cell excitement

A neural network and circuit structure technology, applied in the field of neural network circuit structure with variable neuron excitability, to achieve the effect of improving learning efficiency, strong robustness and fault tolerance

Inactive Publication Date: 2019-04-19
BEIJING UNIV OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] 3. Non-convexity

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 circuit structure capable of changing nerve cell excitement
  • Neural network circuit structure capable of changing nerve cell excitement
  • Neural network circuit structure capable of changing nerve cell excitement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Below in conjunction with accompanying drawing and specific embodiment the present invention will be further described:

[0033] Such as figure 1 Shown is a schematic diagram of an artificial neural network. A layer of neurons between the output layer and the input layer is called a hidden layer or a hidden layer. Each layer of neurons is fully interconnected with the next layer of neurons, and there is no same-layer connection or cross-layer connection between neurons. Among them, the neurons in the input layer receive external input, the neurons in the hidden layer and the output layer process the signal, and the final result is output by the neurons in the output layer; The output layer neurons are functional neurons with activation functions.

[0034] Such as figure 2The schematic diagram of the parameter interface module is shown. The main control unit uses STC's IAP15F2K61S2 microcontroller as the controller. This controller is a processor that supports IAP te...

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 neural network circuit structure capable of changing nerve cell excitement, which comprises a neural network structure and a parameter interface module, and is characterizedin that the neural network structure is connected with the parameter interface module. According to the invention, the nonlinear state of neuronal excitement during learning of people can be fully approximated; The self-learning capability is achieved, and unknown or uncertain systems can be learned; All quantitative or qualitative information is equipotential distributed and stored in each neuronin the emotional neural network, so that the robustness and the fault tolerance are very high; And a parallel distribution processing method is adopted, so that the high-speed solution searching andoptimizing capability is achieved, the high-speed operation capability of a computer can be exerted, a large number of operations can be carried out quickly, and the learning efficiency is greatly improved.

Description

technical field [0001] The present invention mainly relates to the application of artificial neural network. More specifically, the present invention mainly relates to the neural network circuit structure with variable neuron excitability. This circuit structure can improve learning efficiency through continuous learning, and is mainly suitable for students with learning task crowd. Background technique [0002] Artificial Neural Network (ANN) is a research hotspot in the field of artificial intelligence since the 1980s. It abstracts the human brain neuron network from the perspective of information processing, establishes a simple model, and forms different networks according to different connection methods. In engineering and academia, it is often referred to directly as a neural network or a neural network. A neural network is an operational model consisting of a large number of nodes (or neurons) connected to each other. Each node represents a specific output function...

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): G06N3/063G06N3/08
CPCG06N3/063G06N3/08
Inventor 侯立刚闫帅旗汪子锋彭晓宏耿淑琴
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