We introduce a system for textual entailment that is based on a probabilistic model of entailment. The model is defined using some calculus of transformations on dependency trees, which is...
Results of the GREAT08 Challenge: An image analysis competition for cosmological lensing (2009)
Bridle, Sarah, Balan, Sreekumar T., Bethge, Matthias, Gentile, Marc, Harmeling, Stefan, Heymans, Catherine, ...
We present the results of the GREAT08 Challenge, a blind analysis challenge to infer weak gravitational lensing shear distortions from images. The primary goal was to stimulate new ideas by...
Online Blind Deconvolution for Astronomy (2009)
Harmeling, Stefan, Sra, Suvrit, Hirsch, M., Schölkopf, Bernhard
Atmospheric turbulences blur astronomical images taken by earth-based telescopes. Taking many short-time exposures in such a situation provides noisy images of the same object, where each noisy image...
Using Kernel PCA for Initialisation of Nonlinear Factor Analysis (2008)
Antti Honkela, Stefan Harmeling, Leo Lundqvist, Harri Valpola
The nonlinear factor analysis (NFA) method by Lappalainen and Honkela (2000) [2] is initialised with linear principal component analysis (PCA). Because of the multilayer perceptron (MLP) network used...
Bayesian Estimators for Robins-Ritov's Problem (2007)
Harmeling, Stefan, Toussaint, Marc
Bayesian or likelihood-based approaches to data analysis became very popular in the field of Machine Learning. However, there exist theoretical results which question the general applicability of...
Both authors have equally contributed to this work. (2007)
Stefan Harmeling, Marc Toussaint
Abstract: Bayesian or likelihood-based approaches to data analysis became very popular in the field of Machine Learning. However, there exist theoretical results which question the general...
Probabilistic inference for solving (PO)MDPs (2006)
Tousaint, Marc, Harmeling, Stefan, Storkey, Amos
The development of probabilistic inference techniques has made considerable progress in recent years, in particular with respect to exploiting the structure (e.g., factored, hierarchical or...
Probabilistic inference for solving (PO)MDPs (2006)
Toussaint, Marc, Harmeling, Stefan, Storkey, Amos
The development of probabilistic inference techniques has made considerable progress in recent years, in particular with respect to exploiting the structure (e.g., factored, hierarchical or...
Probabilistic inference for solving (PO)MDPs (2006)
Marc Toussaint, Marc Toussaint, Stefan Harmeling, Stefan Harmeling, Amos Storkey, Amos Storkey
Probabilistic inference for solving (PO)MDPs by
Inlier-Based ICA with an Application to Super-imposed Images (2005)
Meinecke, Frank, Harmeling, Stefan, Müller, Klaus-Robert
This paper proposes a new independent component analysis (ICA) method which is able to unmix overcomplete mixtures of sparce or structured signals like speech, music or images. Furthermore, the...
Inlier-based ICA with an application to superimposed images (2005)
Meinecke, Frank, Harmeling, Stefan, Müller, Klaus-Robert
This paper proposes a new ICA method which is able to unmix overcomplete mixtures of images. Furthermore, the method is designed to be robust against outliers, which is a favorable feature for ICA...
From outliers to prototypes: Ordering data (2005)
Harmeling, Stefan, Dornhege, Guido, Tax, David, Meinecke, Frank, Müller, Klaus-Robert
We propose simple and fast methods based on nearest neighbors that order objects from high-dimensional data sets from typical points to untypical points. On the one hand, we show that these...
Inlier-based ICA with an application to super-imposed images (2005)
Meinecke, Frank, Harmeling, Stefan, Müller, Klaus-Robert
This paper proposes a new ICA method which is able to unmix overcomplete mixtures of images. Furthermore, the method is designed to be very robust against outliers, which is a favorable feature for...
From outliers to prototypes: ordering data (2005)
Harmeling, Stefan, Dornhege, Guido, Tax, David, Meinecke, Frank, Müller, Klaus-Robert
We propose simple and fast methods based on nearest neighbors that order objects from high-dimensional data sets from typical points to untypical points. On the one hand, we show that these...
Independent component analysis and beyond (2004)
Independent component analysis (ICA) is a tool for statistical data analysis and signal processing that is able to decompose multivariate signals into their underlying source components. Although the...
Honkela, Antti, Harmeling, Stefan, Lundqvist, Leo, Valpola, Harri
The variational Bayesian nonlinear blind source separation method introduced by Lappalainen and Honkela in 2000 is initialised with linear principal component analysis (PCA). Because of the...
Independent component analysis and beyond (2004)
'Independent component analysis' (ICA) ist ein Werkzeug der statistischen Datenanalyse und Signalverarbeitung, welches multivariate Signale in ihre Quellkomponenten zerlegen kann. Obwohl das...
Independent component analysis and beyond (2004)
'Independent component analysis' (ICA) ist ein Werkzeug der statistischen Datenanalyse und Signalverarbeitung, welches multivariate Signale in ihre Quellkomponenten zerlegen kann. Obwohl das...
Independent component analysis and beyond (2004)
'Independent component analysis' (ICA) ist ein Werkzeug der statistischen Datenanalyse und Signalverarbeitung, welches multivariate Signale in ihre Quellkomponenten zerlegen kann. Obwohl das...
Injecting noise for analysing the stability of ICA components (2004)
Harmeling, Stefan, Meinecke, Frank, Müller, Klaus-Robert
Usually, noise is considered to be destructive. We present a new method that constructively injects noise to assess the reliabilityand the grouping structure of empirical ICA component estimates. Our...
Robust ICA for Super-Gaussian Sources (2004)
Meinecke, Frank, Harmeling, Stefan, Müller, Klaus-Robert
Most ICA algorithms are sensitive to outliers. Instead of robustifying existing algorithms by outlier rejection techniques, we show how a simple outlier index can be used directly to solve the ICA...
Independent component analysis and beyond (2004)
'Independent component analysis' (ICA) ist ein Werkzeug der statistischen Datenanalyse und Signalverarbeitung, welches multivariate Signale in ihre Quellkomponenten zerlegen kann. Obwohl das...
Independent component analysis and beyond (2004)
'Independent component analysis' (ICA) ist ein Werkzeug der statistischen Datenanalyse und Signalverarbeitung, welches multivariate Signale in ihre Quellkomponenten zerlegen kann. Obwohl das...
Independent component analysis and beyond [Elektronische Ressource] / (2004)
Potsdam, University, Diss., 2004.
Antti Honkela, Stefan Harmeling, Leo Lundqvist, Harri Valpola
Abstract. The variational Bayesian nonlinear blind source separation method introduced by Lappalainen and Honkela in 2000 is initialised with linear principal component analysis (PCA). Because of the...
Robust ICA for Super-Gaussian Sources (2004)
Frank C. Meinecke, Stefan Harmeling, Klaus-robert Müller
Abstract. Most ICA algorithms are sensitive to outliers. Instead of robustifying existing algorithms by outlier rejection techniques, we show how a simple outlier index can be used directly to solve...
Antti Honkela, Stefan Harmeling, Leo Lundqvist, Harri Valpola
Abstract. The variational Bayesian nonlinear blind source separation method introduced by Lappalainen and Honkela in 2000 is initialised with linear principal component analysis (PCA). Because of the...
Independent component analysis and beyond / (2004)
Potsdam, University, Diss., 2004 (Nicht für den Austausch).
Andreas Ziehe, Motoaki Kawanabe, Stefan Harmeling, Te-won Lee, Jean-francois Cardoso, Erkki Oja, ...
We propose two methods that reduce the post-nonlinear blind source separation problem (PNLBSS) to a linear BSS problem. The first method is based on the concept of maximal correlation: we apply the...
Andreas Ziehe, Motoaki Kawanabe, Stefan Harmeling, Klaus-robert Müller
At the previous workshop (ICA2001) we proposed the ACE-TD method that reduces the post-nonlinear blind source separation problem (PNL BSS) to a linear BSS problem [18]. The method utilizes the...
Andreas Ziehe, Motoaki Kawanabe, Stefan Harmeling, Klaus-Robert Müller, Fraunhofer First. Ida, Te-won Lee, ...
We propose two methods that reduce the post-nonlinear blind source separation problem (PNLBSS) to a linear BSS problem. The first method is based on the concept of maximal correlation: we apply the...
Analysing ICA Components by Injecting Noise (2003)
Stefan Harmeling, Frank Meinecke, Klaus-robert Müller
Usually, noise is considered to be destructive. We present a new method that constructively injects noise to assess the reliability and the group structure of empirical ICA components. Simulations...
Kernel feature spaces and nonlinear blind source separation (2002)
Stefan Harmeling, Andreas Ziehe, Motoaki Kawanabe, Klaus-robert Müller
In kernel based learning the data is mapped to a kernel feature space of a dimension that corresponds to the number of training data points. In practice, however, the data forms a smaller submanifold...
Kernel feature spaces and nonlinear blind source separation (2002)
Stefan Harmeling, Andreas Ziehe, Motoaki Kawanabe, Klaus-robert Müller
In kernel based learning the data is mapped to a kernel feature space of a dimension that corresponds to the number of training data points. In practice, however, the data forms a smaller submanifold...
Separation of post-nonlinear mixtures using ACE and temporal decorrelation (2001)
Andreas Ziehe, Motoaki Kawanabe, Stefan Harmeling
ziehe,nabe,harmeli,klaus§ We propose an efficient method based on the concept of maximal correlation that reduces the post-nonlinear blind source separation problem (PNL BSS) to a linear BSS...
Nonlinear blind source separation using kernel feature spaces (2001)
Stefan Harmeling, Andreas Ziehe, Motoaki Kawanabe, Benjamin Blankertz, Klaus-robert Müller
In this work we propose a kernel-based blind source separation (BSS) algorithm that can perform nonlinear BSS for general invertible nonlinearities. For our kTDSEP algorithm we have to go through...