Friday, April 27, 2007

A (15, 100)-ES Following A Moving Optimum




Here you are a nice video, which I took from EvoWeb Flying Circus, that shows us an Evolution Strategy (ES) following a moving optimum. The ES applied is the so-called Comma ES or (μ, λ)-ES. The Comma word has to do with the mechanism of selection that happens and it is done through a simple way:


There are, in the current generation, μ parents that generate (via mutation and/or recombination) λ offsprings. Then, we select among the λ offsprings the μ best ones which will be the parents for the next generation, even though those λ are worse than their parents. Let me show you an example:


Say that we have 5 parents (μ = 5) and we want to generate 20 offsprings (λ = 20) - so, our evolution strategy is (5, 20)-ES. When the 5 parents have already generated the 20 offsprings, we select the top 5 from those 20 ones. This kind of selection mechanism is interesting because allows us to escape local optima or do hill-climbing to seek better places inside the space defined by the fitness function. Despite the fact that that type of selection procedure permits a temporary deterioration related to the quality of the individuals (offsprings' fitnesses) which will replace their parents in the subsequent generation, it is well suited to problems that have a moving optimum.




The turquoise (or cyan) star is the moving optimum and the function being optimized is the Fletcher-Powell function, see below.

Das Kabinett des Doktor Garu

I found a new blog linking to mine. At first glance it has not so much to do with evolutionary computation (but I should confess that I did not browse so much the blog), however, it seems a nice blog! :)

The author has four papers accepted at GECCO 2007. The most part deals with the application of soft computing.

Even More On The 2007 IEEE Symposium on Computational Intelligence




Peter Chen invited me to visit his blog to read a new posting upon the 2007 IEEE Symposium on Computational Intelligence. He wrote a very nice overview about the Symposium. But there are much more than just the overview, you can also find penguins, birds, aloha pizza, unusual beach wearing style, genetic algorithm with dominance, and much more stuffs! :)

Finally a person is posting more detailed (and nice) informations and stuffs about the 2007 IEEE Symposium on Computational Intelligence. Thank you, Peter, for the nice work! :)

The picture above (which I took from Peter's blog): Peter Chen beside David B. Fogel.

Thursday, April 26, 2007

New Evolutionary Computation Book

There is a new EC book which deals with parameter setting in evolutionary algorithms, an important subject inside EC. Please, read the post at MEDAL Blogging for a more detailed story.

Sunday, April 22, 2007

David Fogel Receives 2007 IEEE Computational Intelligence Society Meritorious Service Award




David B. Fogel received the Meritorious Service Award, from IEEE, for his exceptional administrative, managerial and leadership achievement; proposal and/or implementation of innovative new CIS [Computational Intelligence Society] programs; dedication to the growth and advancement of CIS and its geographic and technical entities.

Fogel received the award during the 2007 IEEE Symposium on Computational Intelligence. He stated:


"'It’s been my great pleasure to be able to participate with many wonderful colleagues for over 13 years,' said Dr. Fogel. 'It’s very nice to receive this recognition, but really it is a recognition of everything that we as a society of volunteers have been able to create together, and I look forward to many more years of working with my colleagues in the IEEE Computational Intelligence Society to advance the state of our art for the generations who follow us.'"


See here for the whole story.

Friday, April 20, 2007

More On 2007 IEEE Symposium on Computational Intelligence Blogging




Our blog friend, Julian Togelius, has a nice summary of the 2007 IEEE Symposium on Computational Intelligence, see here.

Well, I do not know if I am wrong, but it seems that so few persons are blogging upon that IEEE event. What is a pity, of course.

Thursday, April 19, 2007

Evolving Shape Recognition Through Simulated Evolution



From an old news from NASA:

"Noever and his colleagues plan to develop the 'Book of Life' technology using neural networks and evolvable hardware - rewriteable computer chips capable of learning multiple patterns or images as they process information. Testing the system's image recognition ability and cataloging life forms from Earth will be the first of three project phases."


For the whole story, see here

Wednesday, April 18, 2007

David E. Goldberg Talks To EvoNews




Here you are three nice interviews/short-talks with David E. Goldberg from the University of Illinois at Urbana-Champaign (UIUC), see below.

1 - David E. Goldberg Talks To EvoNews.

2 - David Goldberg's invited talk at EuroGP 2003 - From Competence to Efficiency to Innovation Support.

3 - Professor David Goldberg on 'The Design of Innovation'.

For a searchable version of his book, The Design Of Innovation, see here.

An Interview With David Fogel



See here an interview with David Fogel.

Monday, April 16, 2007

2007 IEEE Symposium on Computational Intelligence Blogging




Finally some (I should confess that I found only four) bloggers are posting upon the 2007 IEEE Symposium on Computational Intelligence. See here, here, here and here - If you understand these later two, please, tell me! :)

Optimization Algorithm Toolkit (OAT)

Jason Brownlee has moved his initial project to SourceForge. Now it is called Optimization Algorithm Toolkit (OAT).

Evolving Waves Through Simulated Evolution



I found via MEDAL Blogging a post upon the application of a genetic algorithm to improve the efficiency of a wave power generator, see here.

Sunday, April 15, 2007

NASA Administrator Michael Griffin Cites Genetic Algorithms

Sunday, April 08, 2007

Evolving Hardware Through Simulated Evolution

I found via Grey Thumb an interesting article upon evolvable hardware made by a team of Norwegian researchers. Their hardware is designed via simulated evolution and this kind of approach can save lots of important resources, such as human work, material, etc. Let alone the possibility that it also can find a design which has not been seen yet.

2006 IEEE Frank Rosenblatt Technical Field Award




Lawrence J. Fogel (March 2, 1928 - February 18, 2007) - see picture above - was the first recipient of the IEEE Frank Rosenblatt Technical Field Award for his extraordinary and pioneer achievements in computational intelligence and evolutionary computation (see here).

Below1 there is the three pages program for Dr. Fogel's IEEE Frank Rosenblatt Award (for a bigger resolution, see here).





Lawrence Fogel - along with Ingo Rechenberg, Hans-Paul Schwefel, Kenneth De Jong, and others - also holds the Evolutionary Computation Pioneer Awards

Here you are the complete list of the Evolutionary Computation Pioneer Awards recipients:



Recipients

2005: Kenneth De Jong

2004: Richard Friedberg

2003: John H. Holland

2002: Ingo Rechenberg
2002: Hans-Paul Schwefel

2001: Michael Conrad

2000: George Box

1999: Alex S. Fraser

1998: Lawrence J. Fogel




--------------------------------------------------------------
--------------------------------------------------------------

Notes:

1 - The image was taken from the Natural Selection Inc. website.

--------------------------------------------------------------
--------------------------------------------------------------

Saturday, April 07, 2007

Bionics And Evolution-Technique




I found an interesting news upon Ingo Rechenberg work and his team at theTechnical University Berlin. The news reports how Rechenberg is applying the "research" already done by the nature to solve real world problems. Among those nature "technology" we have the lotus effect, the gecko effect, the analysis of bird flight to build safer airplane wings, the sand skink effect, and etc.

Take a moment and read all those nice informations upon Rechenberg's work! :)

Friday, April 06, 2007

IEEE Symposium Series on Computational Intelligence 2007

I have noticed that almost no one is blogging upon the IEEE Symposium Series on Computational Intelligence 2007, which was held in Hawaii. Through Technorati, I found only two blogs reporting something on the IEEE Symposium Series on Computational Intelligence 2007. Our blog friend, Julian Togelius is there (Aloha!).

Here you are the complete agenda:

IEEE Symposium on Computational Intelligence in Image and Signal Processing (CIISP 2007)

IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL 2007)

IEEE Symposium on Computational Intelligence and Data Mining (CIDM 2007)

IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB 2007)

IEEE Symposium on Computational Intelligence and Games (CIG 2007)

IEEE Symposium on Computational Intelligence in Scheduling (CI-Sched 2007)

IEEE Symposium on Foundations of Computational Intelligence (FOCI'07)

IEEE Symposium on Computational Intelligence in Multicriteria Decision Making (MCDM '07)

IEEE Symposium on Artificial Life (CI-ALife'07)

IEEE Swarm Intelligence Symposium (SIS2007)

IEEE Symposium on Computational Intelligence in Security and Defense Applications (CISDA 2007)

IEEE Workshop on Evolvable and Adaptive Hardware (WEAH2007)


Maybe, that blogging lack has to do with the fact that the IEEE Symposium Series on Computational Intelligence 2007 was concluded yesterday and the hot news is comming soon...

... Or some bloggers are very (as we say in Portuguese) bairrista! :)

Monday, April 02, 2007

Evolutionary Computation And YouTube.com

I found some interesting videos upon evolutionary computation at YouTube.com.

Here you are:


1 - Genetic Algorithm Evolves CA dog maze



2 - Dr. Mario Played By A 6th-Generation Genetic Algorithmsee note 1 below



Note 1: Please, do not ask me what a 6th-Generation Genetic Algorithm is. I even do not know what a Competent Genetic Algorithm is!

3 - Evolution Of Neuro-Controllers For A Flapping-Wing Animatsee note 2 below



Note 2: This one applies a Multi-Objective Genetic Algorithm.

4 - Evolved Fuzzy Controllers



5 - Evolution Of Morphology And Behavior



For more videos, see here.
Charles Darwin Has A Posse Check Google Page Rank