Learn More
While classical kernel-based learning algorithms are based on a single kernel, in practice it is often desirable to use multiple kernels. Lanckriet et al. (2004) considered conic combinations of kernel matrices for classification, leading to a convex quadratically constrained quadratic program. We show that it can be rewritten as a semi-infinite linear(More)
Main idea: search for anomalies in the data without training on the clean data. Advantages: no need for training, no need for extensive amount of clean data. Reproduce the state-of-the-art results on the KDD Cup (DARPA '98) dataset (with the main focus on one-class SVM). Investigate the methods from the machine learning point of view. Investigate the(More)
Brain-computer interfaces (BCIs) involve two coupled adapting systems--the human subject and the computer. In developing our BCI, our goal was to minimize the need for subject training and to impose the major learning load on the computer. To this end, we use behavioral paradigms that exploit single-trial EEG potentials preceding voluntary finger movements.(More)
While classical kernel-based learning algorithms are based on a single kernel, in practice it is often desirable to use multiple kernels. Lankriet et al. (2004) considered conic combinations of kernel matrices for classification , leading to a convex quadratically constraint quadratic program. We show that it can be rewritten as a semi-infinite linear(More)
Application and development of specialized machine learning techniques is gaining increasing attention in the intrusion detection community. A variety of learning techniques proposed for different intrusion detection problems can be roughly classified into two broad categories: supervised (classification) and unsupervised (anomaly detection and clustering).(More)
We introduce a new algorithm building an optimal dyadic decision tree (ODT). The method combines guaranteed performance in the learning theoretical sense and optimal search from the algorithmic point of view. Furthermore it inherits the explanatory power of tree approaches, while improving performance over classical approaches such as CART/C4.5, as shown on(More)
This paper introduces a new method using dyadic decision trees for estimating a classification or a regression function in a multi-class classification problem. The estimator is based on model selection by penalized empirical loss minimization. Our work consists in two complementary parts: first, a theoretical analysis of the method leads to deriving(More)
BACKGROUND Support Vector Machines (SVMs)--using a variety of string kernels--have been successfully applied to biological sequence classification problems. While SVMs achieve high classification accuracy they lack interpretability. In many applications, it does not suffice that an algorithm just detects a biological signal in the sequence, but it should(More)
The submissions for the BCI competition 2003 to the Graz dataset are evaluated. Results: Nine results were submitted from 7 groups. One submission contained only class labels for each trial, no continuous information in magnitude nor in time. For this reason, no time-variation could be obtained. Figure 2 shows the time courses of the error rate, the mean(More)
Brain-computer interfaces require effective online processing of electroencephalogram (EEG) measurements, e.g., as a part of feedback systems. We present an algorithm for single-trial online classification of imaginary left and right hand movements, based on time-frequency information derived from filtering EEG wideband raw data with causal Morlet wavelets,(More)