Accepted WCCI 2012 Hybrid Competitions
Accepted FUZZ-IEEE 2012 Competitions
|Learning fuzzy systems from data||Xiao-Jun Zeng and Yingjie Yang|
Accepted IJCNN 2012 Competitions
|Mario AI Championship: Turing Test Track||Noor Shaker, Julian Togelius, and Georgios N. Yannakakis|
|Classification of Psychiatric Problems based on Saccades||Wlodzislaw Duch, Edward Gorzelanczyk, and Tomasz Piotrowski|
IEEE WCCI 2012 Hybrid Competitions
By Chang-Sing Lee and Olivier Teytaud
The technique of Monte Carlo Tree Search (MCTS) has revolutionized the field of computer game-playing, and is starting to have an impact in other search and optimization domains as well.Today, programs such as MoGo/MoGoTW, Crazy Stone, Fuego, Many Faces of Go, and Zen have achieved a level of play that seemed unthinkable only a decade ago. These programs are now competitive at a professional level for 9 x9 Go and amateur Dan strength on 19x19. This competition will feature play between:
Humans (Taiwanese Professional Go Players):
- Chun-Hsun Chou (9P)
- Ping-Chiang Chou (5P)
- Joanne Missingham (5P)
- Kai-Hsin Chang (4P)
Computer Go Programs :
- MoGo/MoGoTW (France / Taiwan)
- Fuego (Canada)
- Many Faces of Go (USA)
- Zen (Japan)
Computational intelligence (CI)-based approaches for long-term forecasting of the energy time series (CIFE)
By Hossein Hassini, Majid Abdollahzade and Arash Miranian
In today’s world with its ever increasing population, forecast of different energy indices, e.g. price, demand and consumption poses itself as an important task for the governments and policy-makers as well as the businessmen involved in energy trading. Influenced by many factors and uncertain phenomena such as population, various economic indicators and occurrence of war, forecasting of energy time series, especially in long-term horizons, is challenging.
Providing long-term outlook for energy indices is highly valuable and beneficial. Evaluation of the CI-based techniques for long-term forecasting of energy indices is the main objective of this competition. Accordingly, we aim at discovering how accurate the different CI-based can forecast various energy time series with different frequencies.
[Read more ...]
By Philip Hingston
The IEEE Computational Intelligence Society is providing a cash prize for this competition, which challenges researchers to create a bot for UT2004 (a first-person shooter) that can fool opponents into thinking it is another human player. The format will be similar to that of the BotPrize Competition (the 2012 BotPrize Competition has not yet been confirmed, but we hope that it will take place at the IEEE Conference on Computational Intelligence and Games in Granada, Spain, 12-15 September, 2012).
By Philipp Rohlfshagen, David Robles and Simon Lucas
Ms. Pac-Man, one of the most successful arcade games ever, is a challenging real-time video game where Ms. Pac-Man, controlled by the player using a four-way joystick, has to collect pills for points and, at the same time, avoid being eaten by any of the four ghosts chasing her. Traditionally, the game is viewed from the perspective of Ms. Pac-Man and several competitions have taken place in the past where controllers were developed to direct Ms. Pac-Man throughout the game. However, the game also provides an excellent environment for testing multi-agent strategies by controlling the team of ghosts; here the goal is to minimise the overall score achieved by Ms. Pac-Man.
By Diego Perez, Philipp Rohlfshagen, Simon Lucas and David Robles
The Travelling Salesman Problem (TSP) is one of the best known optimisation problems in operations research. The Physical Travelling Salesman Problem (PTSP) adds an interesting twist to the TSP: the salesman is now physically embodied and can be moved across a two-dimensional map by applying sideway rotations and throttling. The goal of this single-player real-time game is to navigate a set of waypoints as quickly as possible, circumventing any obstacles that are in the way. The PTSP thus requires participants to find an optimal path connecting all waypoints while steering the salesman, making it a challenging and non-trivial game where both planning and reactiveness are required.
By Noor Shaker, Julian Togelius and Georgios Yannakakis
The Turing test track of the competition is about creating Mario controllers that play the game in a human-like manner. Competitors use the same java interface used for the learning track. The winner is decided by the vote of the audience, who gets to watch videos of human and computer players who play the same levels, and try to tell the humans from the algorithms. A demo of the track (with just a few entrants and no official results) ran at the CIG conference in August 2012 in South Korea.
[Read more ...]
IEEE CEC 2012 Competitions
By Ke Tang, Zhenyu Yang and Thomas Weise
The competition is organized in company with the Special Session on Evolutionary Computation for Large Scale Global Optimization. The competition allows participants to run their own algorithms on 20 benchmark functions, each of which is of 1000 dimensions. The purpose of this competition is to compare different algorithm on the exactly same platform. The experiments will take about 205 hours with the Matlab version on a PC with 2.40GHz CPU, and 104 hours with the Java version on a PC with 2.2GHz CPU. Each participant (or research group) is invited to submit a paper to the special session to present their algorithm as well as the results obtained. Details of the set of scalable functions and requirements on the simulation procedure are available at http://staff.ustc.edu.cn/~ketang/cec2012/lib/lsgo_benchmark.zip. Researchers are welcome to apply any kind of approach to the test suite. Interested participants are welcome to report their approaches and results in a paper and submit it to the above mentioned special session via the online submission system of WCCI-2012. Alternatively, the results can also be submitted in the form of a brief technical report, which should be sent to Ke Tang directly. Submissions in both forms will be considered together for the final evaluation of the competition.
[Read more… ]
By Changhe Li, ShengXiang Yang and David Pelta
Many real-world optimization problems are dynamic optimization problems (DOPs), where changes may occur over time regarding the objective function, decision variable, and constraints, etc. DOPs raise big challenges to traditional optimization methods as well as evolutionary algorithms (EAs). The last decade has witnessed increasing research efforts on handling dynamic optimization problems using EAs and other metaheuristics, and a variety of methods have been reported across a broad range of application backgrounds. The aim of this competition is to promote research on the applications of Evolutionary Computation (EC), including nature-inspired computational models, meta-heuristic techniques, and other intelligent methods, to the solution of DOPs.
FUZZ-IEEE 2012 Competitions
By By Xiao-Jun Zeng and Yingjie Yang
Learning from data is one of the most fundamental issues in the theory and application of computational intelligence. In the last two decades, fuzzy system approach has made the significant progress in this very important area. The objectives of this competition are to evaluate the quality and accuracy of fuzzy systems as an approach of learning from data, to identify the weaknesses of the existing methods and algorithms when applying to real data, and to develop new methods. To achieve these objectives, we have designed the following competition problem:
[Read more ...]
IJCNN 2012 Competitions
By Noor Shaker, Julian Togelius, and Georgios N. Yannakakis
The Turing Test Track of the Mario AI Championship addresses the problem of how to create human-like behaviour in game characters. As a common approach to doing this is to record human play traces and try to learn a model, it also addresses the problem of how to learn to imitate human playing style in unseen environments based on limited amounts of data.
The competition works as follows: competitors submit controllers to the competition, following the same format as the established Gameplay Track of the competition, that are able to play any level of the benchmark Infinite Mario Bros game (a clone of Super Mario Bros). The competition organizers create a series of videos, showing each of the submitted controllers as well as human players of varying skill playing on unseen levels. The audience at the conference then gets to vote on the most human-like controllers in a series of forced-choice paired comparisons, where two videos are shown side-to-side (where each video shows either a submitted controller or a human playing the game; it is possible that both videos show AI controllers, or both videos show humans). The winner is simply the controller that gets the most votes for humanness.
[Read more ...]
By Wlodzislaw Duch, Edward Gorzelanczyk,and Tomasz Piotrowski
Eye movement recordings may serve as an early differential diagnostic tool for many psychiatric conditions. In this competition recordings of eye movements from a saccadometer will be used to distinguish between people suffering from Parkinson disease, Alzheimer disease, schizophrenia, and opioid drug addiction.
Number of records: about 150
Evaluation: accuracy of classification rates for each condition, final ranking based on balanced accuracy.
Separately we shall evaluate how useful are the methods to understand which features of the signal are important for such classification. More information on this second goal of the competition will be given in early February 2012.
[Read more ...]