Datasets And Contests

STYLE
Name: Your Name Here
Source: Name of the dataset url (text)
Description: 1-2 sentences about the dataset or contest.

Datasets

Name: Gail Carpenter
Source: UCI Machine Learning Repository http://mlearn.ics.uci.edu/MLRepository.html
Description: The UCI Repository is a widely used resource, with over 100 datasets. Many are small-scale, useful for model development.

Name: Gail Carpenter
Source: UCI Knowledge DIscovery in Databases (KDD) Archive [http://kdd.ics.uci.edu/ -> http://kdd.ics.uci.edu/]]
Description: This UCI Archive links to large datasets, useful for testing models on realistic data.
Datasets include:
20 Newsgroups Data
Australian Sign Language Data
High-quality Australian Sign Language Data
1990 US Census Data
Census-Income Database
COIL Data
Corel Image Features
E. Coli Genes
EEG Data
El Nino Data
Entree Chicago Recommendation Data
CMU Face Images
Forest CoverType
The Insurance Company Benchmark (COIL 2000)
Internet Usage Data
IPUMS Census Data
Japanese Vowels
KDD CUP 1998 Data
KDD CUP 1999 Data
M. Tuberculosis Genes
Movies
Microsoft Anonymous Web Data
MSNBC Anonymous Web Data
NSF Research Awards Abstracts 1990-2003
Pioneer-1 Mobile Robot Data
Pseudo Periodic Synthetic Time Series
Reuters-21578 Text Categorization Collection
Reuters Transcribed Subset
Robot Execution Failures
Synthetic Control Chart Time Series
Syskill Webert Web Data
UNIX User Data
Volcanoes on Venus

Name: Gail Carpenter
Source: Other datasets linked from the UCI Repository http://mlearn.ics.uci.edu/MLOther.html
Description: Datasets in this list:
DELVE - Data for Evaluating Learning in Valid Experiments (University of Toronto)
CMU AI Repository
MLnet Archive at GMD
Synthetic Classification Data Sets (SCDS)
StatLib
Netlib
Information Retrieval Datasets
MLC++
National Space Science Data Center (NSSDC)
Neuroprose Archive
SCOP (Structural Classification of Proteins)
Brookhaven Protein Database Gopher
DOE Biology Information Center
WordNet http://wordnet.princeton.edu/
US Bureau of Census http://www.census.gov/
NIST (National Institute of Standards and Technology http://www.nist.gov//
Face Recognition Dataset
RISE: Repository of online Information Sources used in information Extraction tasks

Contests

Name: Gail Carpenter
Source: Netflix Prize http://www.netflixprize.com/indexl
Description: Netflix provides movie ratings by thousands of users. A million dollar prize, as well as yearly Progress Prizes, are offered to contestants who can improve rating predictions up to a criterion level. According to the website (4-08), there are over 35,000 contestants from 170 countries.

Name: Gail Carpenter
Source: WCCI 2008 Competitions http://www.wcci2008.org/competitions.htm l
Description: Competitions for the June, 2008, WCCI (Hong Kong) include problems on games, navigation, data mining, and optimization. From the website:
WCCI 2008 will host competitions to stimulate research in computational intelligence, promote fair evaluations, and attract students. The competitions will take place between December 2007 and May 2008. For questions, please contact the Competitions Chairs Isabelle Guyon at isabelle@clopinet.com for IJCNN2008, Leszek Rutkowski at lrutko@kik.pcz.czest.pl for FUZZ-IEEE2008, or Philip Hingston at p.hingston@ecu.edu.au for CEC2008.
Games
Ms Pac-man: Simon Lucas - Started - Deadline March 8, 2008
Neural Network Othello: Simon Lucas - Started - Deadline March 8, 2008
Navigation
Car Racing Competition: Julian Togelius - February 1st 2008 - May 25, 2008
Robotic Car Racing: Simon Lucas
Pedestrian Trajectory for Collision Avoidance: Nicolas Brodu - Started - Deadline April 30, 2008
Data mining
Ford Classification Challenge: Mahmoud Abou-Nasr - Started - March 08, 2008
Artificial Neural Network and Computational Intelligence Forecasting Competition: Sven F. Crone
Causality Challenge: Causality Workbench Team - Started - Deadline April 30, 2008
Optimization
Mountains or Molehills: Scale-Invariant Optimisation Competition: Cara MacNish - Started - Deadline May 1st, 2008
Large Scale Global Optimization: Ke Tang - Started - Deadline March 1, 2008
Problem Specific Multi-objective Optimization: Walking Fish Group

Name: Gail Carpenter
Source: IJCNN'07 Challenge http://www.clopinet.com/isabelle/Projects/agnostic/ l
Description: IJCNN'07 sponsored a workshop and challenge to investigate agnostic learning vs. prior knowledge. Winners presented their work at the conference.