Research page of Timo Similä
I am currently working in privat sector but this page should have the
up-to-date information on my scientific career.
Research
I have worked in various research positions at the
Laboratory of Computer and
Information Science at Helsinki
University of Technology from 2001 to 2007. My research
interests included information visualization, dimensionality reduction,
prediction and multivariate data analysis in general.
Teaching
I was the course assistant for
Digital Signal
Processing and Filtering during the autumn term 2002 and the
spring terms 2006 and 2007.
Publications
- Zhu Z, Similä T, Corona F.
Supervised distance preserving projections.
Neural Processing Letters.
Volume 38, Number 3, Pages 445-463, 2013.
- Similä T, Tikka J.
Combined input variable selection and model complexity
control for nonlinear regression.
Pattern Recognition Letters.
Volume 30, Number 3, Pages 231-236, 2009.
- Similä T, Tikka J.
Input selection and shrinkage in multiresponse linear
regression.
Computational Statistics & Data Analysis.
Volume 52, Number 1, Pages 406-422, 2007.
- Similä T.
Majorize-minimize algorithm for
multiresponse sparse regression.
IEEE International Conference on Acoustics, Speech,
and Signal Processing (ICASSP).
Honolulu, HI, USA.
April 15-20, 2007.
Volume II,
Pages 553-556.
- Hakala R, Similä T, Sirola M, Parviainen J.
Process state and progress visualization using
self-organizing map.
International Conference on Intelligent Data
Engineering and Automated Learning (IDEAL).
Burgos, Spain.
September 20-23, 2006.
Pages 73-80.
-
Similä T, Tikka J.
Common subset selection of inputs in multiresponse
regression.
IEEE International Joint Conference on Neural Networks
(IJCNN).
Vancouver, BC, Canada.
July 16-21, 2006.
Pages 1908-1915.
- Similä T. Self-organizing map visualizing
conditional quantile functions with multidimensional
covariates.
Computational Statistics & Data Analysis.
Volume 50, Number 8, Pages 2097-2110, 2006.
- Similä T, Tikka J. Multiresponse sparse
regression with application to multidimensional
scaling.
International Conference on Artificial Neural
Networks (ICANN).
Warsaw, Poland.
September 11-15, 2005.
Pages 97-102.
(Matlab function
mrsr.m)
- Similä T, Laine S. Visual approach to supervised
variable selection by self-organizing map.
International Journal of Neural Systems.
Volume 15, Numbers 1-2, Pages 101-110, 2005.
- Similä T. Self-organizing map learning nonlinearly
embedded manifolds.
Information Visualization.
Volume 4, Number 1, Pages 22-31, 2005.
- Laine S, Similä T.
Using SOM-based data binning to support supervised
variable selection.
International Conference on Neural Information
Processing (ICONIP).
Science City, Calcutta, India.
November 22-25, 2004.
Pages 172-180.
- Hätönen K, Laine S, Similä T. Using the
logsig-function to integrate expert
knowledge to self-organizing map based analysis.
IEEE International Workshop on Soft Computing in
Industrial Applications (SMCia).
Binghamton, NY, USA.
June 23-25, 2003.
Pages 145-150.
Theses
|