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

Nerve network system for realizing genetic algorithm

A genetic algorithm and neural network technology, applied in the biological neural network model, physical realization, genetic model, etc., can solve the limitation of code string length, population size fitness value function genetic operation operator complexity limitation, hardware genetic algorithm is expensive , operating clock frequency, memory response time limit, etc.

Inactive Publication Date: 2003-10-22
BEIJING UNIV OF TECH
View PDF0 Cites 39 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the current research of hardware genetic algorithm, the FPGA-based hardware implementation scheme aims to improve the running speed of genetic algorithm through the high-speed computing performance of hardware, but the operating clock frequency of such scheme is limited by the response time of memory
The genetic algorithm needs a large amount of memory to store the information of the population, so the memory bottleneck is inevitable, and the use of high-speed memory will also make the hardware genetic algorithm expensive
In addition, the hardware genetic algorithm also faces limitations in the length of the coded string, the size of the population, the fitness value function, and the complexity of the genetic operator.
In short, the hardware genetic algorithm is far from solving the problem of the running speed of the genetic algorithm.

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
  • Nerve network system for realizing genetic algorithm
  • Nerve network system for realizing genetic algorithm
  • Nerve network system for realizing genetic algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] In this embodiment, the process of optimizing the classic test function (Needle-in-a-Haystack) of the system is taken as an example to illustrate the working process of the system. The function of finding a needle in a haystack requires finding the maximum value point, and its solution space terrain (Landscape) is as follows Figure 14 As shown, there is a local maximum point y=2748.78 in each of the four corners of the domain, and the only global maximum point y in the middle max=f(0,0)=3600 is surrounded by countless global minimum points isolated in a small area, which makes it difficult to optimize the global maximum point, so this function is widely used for testing Algorithm optimization ability. In view of the fact that the topography of the solution space of the needle-in-a-haystack function changes drastically in its central area, the optimization in this area requires high precision. In this example, a real-coded genetic algorithm is used, and the parameters ...

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 is nerve net system which can realize heredity arithmetic. It is made up of computer nerve net model component and the interfaces. The character lies in: 1. after that the computer setsthe population size, coding type and length, heredity operation probability and the arithmetic ending condition of the arithmetic, the nerve net uses population size to realize the whole heredity operation including selection, crossing, mutation and personal adaptability value, and outputs the optimized calculation and result through computer; 2. designs the heredity operation nerve net model which can realize multi-father crossing operation and multi-gene mutation operation, realizes the two operation of two-value coding heredity arithmetic and real number coding heredity arithmetic.

Description

Technical field: [0001] The neural network system for realizing the genetic algorithm relates to a physical realization system of the genetic algorithm, in particular to a physical realization system of the genetic algorithm based on the neural network module. The purpose of this system is to improve the optimization calculation efficiency of genetic algorithm, which belongs to the field of optimization calculation of artificial intelligence. Background technique: [0002] The genetic algorithm realizes the search and optimization of the solution space by simulating evolution, and its flow chart is as follows: Figure 17 As shown, the general steps are as follows: [0003] The first step is to initialize, set the evolution algebra to 0, randomly generate the population code of the 0th generation, and evaluate the fitness value of each individual in the population; [0004] The second step is to judge whether the optimization criterion is met according to the preset terminat...

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): G06N3/06G06N3/12
Inventor 龚道雄阮晓钢
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