Projects per year
Abstract
Methods that find insightful lowdimensional projections are essential to effectively explore highdimensional data. Principal Component Analysis is used pervasively to find low dimensional projections, not only because it is straightforward to use, but it is also often effective, because the variance in data is often dominated by relevant structure. However, even if the projections highlight real structure in the data, not all structure is interesting to every user. If a user is already aware of, or not interested in the dominant structure, Principal Component Analysis is less effective for finding interesting components. We introduce a new method called Subjectively Interesting Component Analysis (SICA), designed to find data projections that are subjectively interesting, i.e, projections that truly surprise the enduser. It is
rooted in information theory and employs an explicit model of a user's prior expectations about the data. The corresponding optimization problem is a simple eigenvalue problem, and the result is a tradeo between explained variance and novelty. We present five case studies on synthetic data, images, timeseries, and spatial data, to illustrate how SICA enables users to find (subjectively) interesting projections.
rooted in information theory and employs an explicit model of a user's prior expectations about the data. The corresponding optimization problem is a simple eigenvalue problem, and the result is a tradeo between explained variance and novelty. We present five case studies on synthetic data, images, timeseries, and spatial data, to illustrate how SICA enables users to find (subjectively) interesting projections.
Original language  English 

Title of host publication  Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining  KDD '16 
Place of Publication  New York, NY, USA 
Publisher  Association for Computing Machinery (ACM) 
Pages  16151624 
Number of pages  10 
Volume  August 2016 
ISBN (Print)  9781450342322 
DOIs  
Publication status  Published  13 Aug 2016 
Event  ACM KDD 2016  San Francisco, United States Duration: 13 Aug 2016 → 17 Aug 2016 
Conference
Conference  ACM KDD 2016 

Country  United States 
City  San Francisco 
Period  13/08/16 → 17/08/16 
Keywords
 Exploratory Data Mining
 Dimensionality Reduction
 Information Theory
 Subjective Interestingness
Fingerprint Dive into the research topics of 'Subjectively Interesting Component Analysis: Data Projections that Contrast with Prior Expectations'. Together they form a unique fingerprint.
Projects
 1 Finished

Data Science for the Detection of Emerging Music Styles
De Bie, T. E. P.
1/11/14 → 1/11/16
Project: Research
Profiles

Dr Raul SantosRodriguez
 Department of Engineering Mathematics  Associate Professor of Data Science and Intelligent Systems
Person: Academic