alexa Self-organization and Intelligence | OMICS International
ISSN: 2090-4908
International Journal of Swarm Intelligence and Evolutionary Computation
Make the best use of Scientific Research and information from our 700+ peer reviewed, Open Access Journals that operates with the help of 50,000+ Editorial Board Members and esteemed reviewers and 1000+ Scientific associations in Medical, Clinical, Pharmaceutical, Engineering, Technology and Management Fields.
Meet Inspiring Speakers and Experts at our 3000+ Global Conferenceseries Events with over 600+ Conferences, 1200+ Symposiums and 1200+ Workshops on
Medical, Pharma, Engineering, Science, Technology and Business

Self-organization and Intelligence

Qiangfu Zhao*

System Intelligence Laboratory, University of Aizu, Aizuwakamatsu, Fukushima, Japan

Corresponding Author:
Qiangfu Zhao
System Intelligence Laboratory
University of Aizu, Aizuwakamatsu
Fukushima, Japan
Tel: 81-242-37-2519
E-mail: [email protected]

Received date: February 17, 2014; Accepted date: February 18, 2014; Published date: February 26, 2014

Citation: Qiangfu Zhao (2014) Self-organization and Intelligence. Int J of Swarm Intel Evol Comput 3:e104. doi:

Copyright: © 2014 Zhao Q. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Visit for more related articles at International Journal of Swarm Intelligence and Evolutionary Computation

Abstract

Self-organization (SO) is one of the key issues for generating true intelligence. Without SO, human brains and human societies will just be chaotic systems. The basic SO mechanism is the Leader-Following (LF) behavior. With LF behavior, a complex system can become very well organized after many generations. Without LF behavior, however, even a relatively small dynamic system can become intractable. In fact, the basic learning rule in the well-known Self-Organizing Map (SOM) algorithm is LF. Here, for any given data point, neurons close to the winner tries to imitate the winner, so that they can behave in a similar way for similar data. The basic learning rule in Particle Swarm Optimization (PSO) is also LF. In PSO, each particle tries to imitate the behavior of the local or global leader, while trying to preserve its own search history. Thus, although SOM and PSO are different, both of them are LF based SO algorithms.

Editorial

Self-organization (SO) is one of the key issues for generating true intelligence. Without SO, human brains and human societies will just be chaotic systems. The basic SO mechanism is the Leader-Following (LF) behavior. With LF behavior, a complex system can become very well organized after many generations. Without LF behavior, however, even a relatively small dynamic system can become intractable. In fact, the basic learning rule in the well-known Self-Organizing Map (SOM) algorithm is LF. Here, for any given data point, neurons close to the winner tries to imitate the winner, so that they can behave in a similar way for similar data. The basic learning rule in Particle Swarm Optimization (PSO) is also LF. In PSO, each particle tries to imitate the behavior of the local or global leader, while trying to preserve its own search history. Thus, although SOM and PSO are different, both of them are LF based SO algorithms.

In SOM and PSO neurons or particles just move (in the search space) in a direction so that they can become more similar to the winner or leader after moving. This is nothing but Lamarckian evolution. It is well-known that Lamarckian evolution is not good if the search space is complex or dynamically changing. A better way is Darwinian evolution, and Standard Genetic Algorithm (SGA) is a typical example. From the above discussion we may naturally wonder if GA is also an SO algorithm. In fact it is. In SGA, leaders or individuals with high fitness values have higher opportunity for reproducing offspring, and the whole population will behave similar to the leader(s) after many generations. In SGA, individuals do not “know” the leader to imitate. Good traits are preserved based only on the survival the fittest principle.

It is known that Darwinian evolution like SGA alone is neither efficient nor effective for solving large scale complex problems. A better way is to combine Darwinian and Lamarckian evolutionary algorithms. This kind of hybrids is known as the Memetic Algorithms (MAs). In a MA, good traits of good individuals can be evolved and imitated, and the population can self-organize during evolution. In general, MAs can be very efficient and effective for solving complex problems.

From the above discussions we may see that different algorithms developed in different contexts may actually share the same principle. I believe that the International Journal of Swarm Intelligence and Evolutionary Computation can provide for researchers and practitioners a forum to publish new ideas, new concepts, and new results; and at the same time, a platform to find common theories behind different algorithms and different applications.

Select your language of interest to view the total content in your interested language
Post your comment

Share This Article

Relevant Topics

Recommended Conferences

  • 4th Global Summit and Expo on Multimedia & Artificial Intelligence
    July 19-21, 2018 Rome, Italy
  • International Conference on Artificial Intelligence, Robotics & IoT
    August 21-22, 2018 Paris, France
  • 6th World Convention on Robots and Deep Learning
    September 10-11, 2018 Singapore City, Singapore
  • International Conference on Mechatronics & Robotics
    October 15-16, 2018 Helsinki, Finland

Article Usage

  • Total views: 12025
  • [From(publication date):
    December-2014 - Jul 16, 2018]
  • Breakdown by view type
  • HTML page views : 8236
  • PDF downloads : 3789
 

Post your comment

captcha   Reload  Can't read the image? click here to refresh

Peer Reviewed Journals
 
Make the best use of Scientific Research and information from our 700 + peer reviewed, Open Access Journals
International Conferences 2018-19
 
Meet Inspiring Speakers and Experts at our 3000+ Global Annual Meetings

Contact Us

Agri & Aquaculture Journals

Dr. Krish

[email protected]

+1-702-714-7001Extn: 9040

Biochemistry Journals

Datta A

[email protected]

1-702-714-7001Extn: 9037

Business & Management Journals

Ronald

[email protected]

1-702-714-7001Extn: 9042

Chemistry Journals

Gabriel Shaw

[email protected]

1-702-714-7001Extn: 9040

Clinical Journals

Datta A

[email protected]

1-702-714-7001Extn: 9037

Engineering Journals

James Franklin

[email protected]

1-702-714-7001Extn: 9042

Food & Nutrition Journals

Katie Wilson

[email protected]

1-702-714-7001Extn: 9042

General Science

Andrea Jason

[email protected]

1-702-714-7001Extn: 9043

Genetics & Molecular Biology Journals

Anna Melissa

[email protected]

1-702-714-7001Extn: 9006

Immunology & Microbiology Journals

David Gorantl

[email protected]

1-702-714-7001Extn: 9014

Materials Science Journals

Rachle Green

[email protected]

1-702-714-7001Extn: 9039

Nursing & Health Care Journals

Stephanie Skinner

[email protected]

1-702-714-7001Extn: 9039

Medical Journals

Nimmi Anna

[email protected]

1-702-714-7001Extn: 9038

Neuroscience & Psychology Journals

Nathan T

[email protected]

1-702-714-7001Extn: 9041

Pharmaceutical Sciences Journals

Ann Jose

[email protected]

1-702-714-7001Extn: 9007

Social & Political Science Journals

Steve Harry

[email protected]

1-702-714-7001Extn: 9042

 
© 2008- 2018 OMICS International - Open Access Publisher. Best viewed in Mozilla Firefox | Google Chrome | Above IE 7.0 version
Leave Your Message 24x7