Neural network teaching demonstrating platform

A technology of neural network and demonstration platform, applied in the field of teaching demonstration platform, can solve the problems of no easy-to-understand teaching demonstration platform

Inactive Publication Date: 2012-09-19
陈恩策
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] When showing the role of neural networks, there is no good and easy-to-understand teaching demonstration platform

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 teaching demonstrating platform
  • Neural network teaching demonstrating platform
  • Neural network teaching demonstrating platform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] First, neural network sample learning is performed. Put the prepared digital card on the identification board so that it can figure 1 As shown, cover the position of the corresponding nixie tube. After the card is placed stably, press the button S1, the single-chip microcomputer performs analog / digital sampling, encodes the input signal, and completes a sample learning.

[0019] Replace the math cards, repeat the above sample learning process several times, observe the values ​​displayed on the LCD screen, and when they no longer change, the learning part of the neural network is completed. At this time, LED1 is on, indicating that the learning process has been completed, and the verification and identification process of the neural network to independently identify the odd-even card can be carried out. At the same time, the data completed this time will also be stored in the EEPROM, so that after the power is turned off, the neural network recognition process can be ...

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 teaching demonstrating platform belonging to the field of teaching demonstrating platforms. The change of data such as a learning process weight is dynamically displayed through an actual hardware circuit. Photosensitive resistors are used as sensors and arranged into an identification plate by adopting a similar seven-segment display mode. A digital card is placed on the identification plate, input signals are judged according to different conditions of differential pressure sizes caused by resistance value changes after the photosensitive resistors are shielded so as to be used as samples of neutral network samples. Odd and even are judged through the neutral network self-learning. Data after learning can be stored due to the arrangement of an EEPROM (Electrically Erasable Programmable Readonly Memory), so that the data can be used in actual odd-even detection without being learned after power failure. In addition, the neural network teaching demonstrating platform is provided with an LED lamp and an LCD liquid crystal output, the change of parameters after learning every time can be more visually observed, therefore, the neutral network working principle is well known.

Description

technical field [0001] The patent of the present invention belongs to the field of teaching demonstration platform; especially the demonstration of neural network mathematical model. Background technique [0002] Artificial neural network is a cutting-edge cross-discipline of artificial intelligence that is rapidly developing in the world. In colleges and universities, there are many courses with neural network as the main content. [0003] Due to the strong theoretical nature of artificial neural networks, most students can only rely on simulation and software to verify the functions of neural networks when learning neural network content, without a more intuitive feeling. [0004] When it comes to demonstrating the role of neural networks, there is no good, easy-to-understand teaching demonstration platform. Contents of the invention [0005] In order to enable students to better grasp and understand the basic principles and practical applications of neural networks du...

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): G09B23/18G06N3/06
Inventor 陈恩策黄莹刘超涂光鹏唐厚君
Owner 陈恩策
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap