Accurate splice site prediction using support vector machines (2007)
Sonnenburg, Sören, Schweikert, Gabriele, Philips, Petra, Behr, Jonas, Rätsch, Gunnar
Abstract Background For splice site recognition, one has to solve two classification problems: discriminating true from decoy splice sites for both acceptor and donor sites. Gene finding systems...
Positional Oligomer Importance Matrices (2007)
Zien, Alexander, Sonnenburg, Sören, Philips, Petra, Raetsch, Gunnar
At the heart of many important bioinformatics problems, such as gene finding and function prediction, is the classification of biological sequences, above all of DNA and proteins. In many cases, the...
Accurate Splice Site Prediction (2007)
Sonnenburg, Sören, Schweikert, Gabriele, Philips, Petra, Behr, Jonas, Raetsch, Gunnar
Background For splice site recognition, one has to solve two classification problems: discriminating true from decoy splice sites for both acceptor and donor sites. Gene finding systems typically...
Computing Positional Oligomer Importance Matrices (POIMs) (2007)
Zien, Alexander, Philips, Petra, Sonnenburg, Sören
We show how to efficiently compute Positional Oligomer Importance Matrices (POIMs) which are a novel and powerful way to extract, rank, and visualize higher order (i.e. oligo-nucleotide)...
Accurate Splice Site Prediction Using Support Vector Machines (2007)
Sonnenburg, Sören, Schweikert, Gabriele, Philips, Petra, Behr, Jonas, Raetsch, Gunnar
Background: For splice site recognition, one has to solve two classification problems: discriminating true from decoy splice sites for both acceptor and donor sites. Gene finding systems typically...
Data-dependent analysis of learning algorithms (2005)
This thesis studies the generalization ability of machine learning algorithms in a statistical setting. It focuses on the data-dependent analysis of the generalization performance of learning...
Local complexities for empirical risk minimization (2004)
Bartlett, Peter L, Mendelson, Shahar, Philips, Petra
We present sharp bounds on the risk of the empirical minimization algorithm under mild assumptions on the class. We introduce the notion of isomorphic coordinate projections and show that this leads...
Journal of Machine Learning Research ? (?) 1-20 Submitted 12/02; Published ? (2002)
Shahar Mendelson, Petra Philips
It has been recently shown that sharp generalization bounds can be obtained when the function class from which the algorithm choses its hypotheses is small" in the sense that the Rademacher averages...
Klaus-robert Muller, Petra Philips, Andreas Ziehe
So far blind separation algorithms have been either using information from higher order statistics or from time structure in the data. We propose the use of an error function that merges both types...