Center for Machine Learning and Intelligent Systems
About  Citation Policy  Donate a Data Set  Contact


Repository Web            Google
View ALL Data Sets

Browse Through:

Default Task - Undo

Classification (10)
Regression (3)
Clustering (5)
Other (9)

Attribute Type

Categorical (2)
Numerical (6)
Mixed (2)

Data Type - Undo

Multivariate (250)
Univariate (15)
Sequential (32)
Time-Series (54)
Text (29)
Domain-Theory (10)
Other (8)

Area

Life Sciences (3)
Physical Sciences (1)
CS / Engineering (4)
Social Sciences (0)
Business (1)
Game (0)
Other (1)

# Attributes

Less than 10 (2)
10 to 100 (3)
Greater than 100 (3)

# Instances

Less than 100 (0)
100 to 1000 (5)
Greater than 1000 (5)

Format Type

Matrix (5)
Non-Matrix (5)

10 Data Sets

Table View  List View


1. Amazon Commerce reviews set: The dataset is used for authorship identification in online Writeprint which is a new research field of pattern recognition.

2. Japanese Credit Screening: Includes domain theory (generated by talking to Japanese domain experts); data in Lisp

3. Molecular Biology (Promoter Gene Sequences): E. Coli promoter gene sequences (DNA) with partial domain theory

4. Molecular Biology (Splice-junction Gene Sequences): Primate splice-junction gene sequences (DNA) with associated imperfect domain theory

5. Perfume Data: This data consists of odors of 20 different perfumes. Data was obtained by using a handheld odor meter (OMX-GR sensor) per second for 28 seconds period.

6. Reuter_50_50: The dataset is used for authorship identification in online Writeprint which is a new research field of pattern recognition.

7. SMS Spam Collection: The SMS Spam Collection is a public set of SMS labeled messages that have been collected for mobile phone spam research.

8. Thyroid Disease: 10 separate databases from Garavan Institute

9. Twin gas sensor arrays: 5 replicates of an 8-MOX gas sensor array were exposed to different gas conditions (4 volatiles at 10 concentration levels each).

10. USPTO Algorithm Challenge, run by NASA-Harvard Tournament Lab and TopCoder Problem: Pat: Data used for USPTO Algorithm Competition. Contains drawing pages from US patents with manually labeled figure and part labels.


Supported By:

 In Collaboration With:

About  ||  Citation Policy  ||  Donation Policy  ||  Contact  ||  CML