07/01/2010Semi-supervised local Fisher discriminant analysis for dimensionality reduction by Prof. Sese is published in Machine Learning
When only a small number of labeled samples are available, supervised dimensionality reduction methods tend to perform poorly because of overfitting. We propose a semi-supervised dimensionality reduction method which preserves the global structure of unlabeled samples in addition to separating labeled samples in different classes from each other. The proposed method has an analytic form of the globally optimal solution and it can be computed based on eigen-decomposition. We show the usefulness of the new method with real-world document classification datasets.
http://www.springerlink.com/content/80r2m583ph703632/
14/11/2009Web server shutdown for system maintenance
The web server will be down from 21:00, 22nd, Nov. to 21:00, 24th, Nov. for the system maintenance.
http://cib.cf.ocha.ac.jp/index-e.html
27/10/2009Workshop: Bioinformatics beyond Omics Data Analyses
The center will have an international workshop from 3rd to 4th of Dec, 2009. The workshop welcomes poster presentation by students and PostDocs.
http://cib.cf.ocha.ac.jp/symposium-e.html
25/9/2009Journal Paper by Kei Yura and Steven Hayward is accepted by
Bioinformatics
The manuscript "The interwinding nature of protein-protein interfaces and its implication for protein complex formation " by Kei Yura and Steven Hayward is accepted by Bioinformatics.
http://bioinformatics.oxfordjournals.org/cgi/content/abstract/btp563?ijkey=voOBQz3LSrhqdM2&keytype=ref
25/9/2009Journal Paper by Kei Yura, Sintawee Sulaiman et al. is accepted by
Plant and Cell Physiology
The manuscript "RESOPS: A Database for Analyzing the Correspondence of RNA Editing Sites to Protein Three-Dimensional Structures" by Kei Yura, Sintawee Sulaiman et al. is accepted by Plant and Cell Physiology.
http://pcp.oxfordjournals.org/cgi/content/abstract/50/11/1865
1/8/2009Journal Paper by Prof Kato is accepted by
Bioinformatics
The existing supervised methods for biological network inference
are based only on intra-species information such as gene expression
data. The proposed method exploits cross-species information
in a theoretically well-appointed framework.
http://www.net-machine.net/~katolab/en/misc.html
14/7/2009Journal Paper by Prof Kato is accepted by IJKDB
Inferring the relationship among proteins is a central issue of
computational biology and a diversity of biological assays are utilized
to predict the relationship. However, as experiments are usually
expensive to perform, automatic data selection is employed to reduce the
data collection cost. Although data useful for link prediction are
different in each local sub-network, existing methods cannot select
different data for different processes. Prof Kato et al. have devised a
new algorithm for inferring biological networks from multiple types of
assays. The proposed algorithm is based on transfer learning and can
exploit local information effectively. Each assay is automatically
weighted through learning and the weights can be adaptively different in
each local part.
http://www.net-machine.net/~katolab/en/netinf3.html
1/7/2009Invited survey paper by Prof Kato is published in IEICE
Kernel methods such as the support vector machine
are one of the most successful algorithms in modern machine learning.
Their advantage is that
linear algorithms are extended to non-linear scenarios
in a straightforward way by the use of the kernel trick.
However, naive use of kernel methods is computationally expensive
since the computational complexity typically scales cubically with
respect to the number of training samples.
In this article, we review recent advances in the kernel methods,
with emphasis on scalability for massive problems.
http://search.ieice.org/
1/7/2009Tutorial Workshop on Discrete Algorithms and Machine
Learning
Discrete algorithms and machine learning are useful not only for
computer science. Nowadays, they are becoming a fundamental tool in
every scientific field. Let's learn them to move to the forefront of the
time.
http://bioinfo.is.ocha.ac.jp/daml2009/index-en.html
4/5/2009Prof Kato et al's paper was accepted in IEEE TKDE
The paper accepted in IEEE TKDE extends SVM to apply multi-task learning and shows promising results on a variety of applications. IEEE TKDE is one of the top journals in the field of data mining.
http://www.net-machine.net/~kato/publications.html
22/12/2008Open seimnar on 8th, Jan. 2009
The center is going to hold a seminar on compartive modelling by Professor Jooyoung Lee at KIAS, Korea at the meeting room in Ochanomizu Univerisity We welcome students and researchers interested in the field.
JooyoungLee.html