Papers by Joachim Buhmann
... RUNNING HEAD: Data Clustering and Learning Correspondence: Joachim Buhmann Universität Bonn, ... more ... RUNNING HEAD: Data Clustering and Learning Correspondence: Joachim Buhmann Universität Bonn, Institut für Informatik III, Römerstraße 164, D-53117 Bonn, Germany Phone: +49 228 734 380 Fax: +49 228 734 382 email: [email protected], [email protected] ...
Neural Information Processing Systems, 2003
Clustering aims at extracting hidden structure in dataset. While the prob- lem of finding compact... more Clustering aims at extracting hidden structure in dataset. While the prob- lem of finding compact clusters has been widely studied in the litera- ture, extracting arbitrarily formed elongated structures is considered a much harder problem. In this paper we present a novel clustering algo- rithm which tackles the problem by a two step procedure: first the data are transformed in
Neural Information Processing Systems, 2002
Model selection is linked to model assessment, which is the problem of comparing different models... more Model selection is linked to model assessment, which is the problem of comparing different models, or model parameters, for a specific learning task. For supervised learning, the standard practical technique is cross- validation, which is not applicable for semi-supervised and unsupervised settings. In this paper, a new model assessment scheme is introduced which is based on a notion of stability.
Neural Information Processing Systems, 2002
Abstract: Pairwise data in empirical sciences typically violate metricity, eitherdue to noise or ... more Abstract: Pairwise data in empirical sciences typically violate metricity, eitherdue to noise or due to fallible estimates, and therefore arehard to analyze by conventional machine learning technology. Inthis paper we therefore study ways to work around this problem.
Proceedings of the National Academy of Sciences of the United States of America, Jan 22, 2011
A key barrier to the realization of personalized medicine for cancer is the identification of bio... more A key barrier to the realization of personalized medicine for cancer is the identification of biomarkers. Here we describe a two-stage strategy for the discovery of serum biomarker signatures corresponding to specific cancer-causing mutations and its application to prostate cancer (PCa) in the context of the commonly occurring phosphatase and tensin homolog (PTEN) tumor-suppressor gene inactivation. In the first stage of our approach, we identified 775 N-linked glycoproteins from sera and prostate tissue of wild-type and Pten-null mice. Using label-free quantitative proteomics, we showed that Pten inactivation leads to measurable perturbations in the murine prostate and serum glycoproteome. Following bioinformatic prioritization, in a second stage we applied targeted proteomics to detect and quantify 39 human ortholog candidate biomarkers in the sera of PCa patients and control individuals. The resulting proteomic profiles were analyzed by machine learning to build predictive regres...
Analytical Chemistry, 2005
De novo sequencing of peptides poses one of the most challenging tasks in data analysis for prote... more De novo sequencing of peptides poses one of the most challenging tasks in data analysis for proteome research. In this paper, a generative hidden Markov model (HMM) of mass spectra for de novo peptide sequencing which constitutes a novel view on how to solve this problem in a Bayesian framework is proposed. Further extensions of the model structure to a graphical model and a factorial HMM to substantially improve the peptide identification results are demonstrated. Inference with the graphical model for de novo peptide sequencing estimates posterior probabilities for amino acids rather than scores for single symbols in the sequence. Our model outperforms stateof-the-art methods for de novo peptide sequencing on a large test set of spectra.
IEEE Transactions on Computers, 1991
Abstract|We present an object recognition system based on the Dynamic Link Architecture, which is... more Abstract|We present an object recognition system based on the Dynamic Link Architecture, which is an extension to classical Arti cial Neural Networks. The Dynamic Link Architecture exploits correlations in the ne-scale temporal structure of cellular signals in order to group neurons dynamically into higher-order entities. These entities represent a very rich structure and can code for high level objects. In order to demonstrate the capabilities of the Dynamic Link Architecture we implemented a program that can recognize human faces and other objects from video images. Memorized objects are represented by sparse graphs, whose vertices are labeled by a multi-resolution description in terms of a local power spectrum, and whose edges are labeled by geometrical distance vectors. Object recognition can be formulated as elastic graph matching, which is performed here by stochastic optimization of a matching cost function. Our implementation on a transputer network successfully achieves recognition of human faces and o ce objects from gray level camera images. The performance of the program is evaluated by a statistical analysis of recognition results from a portrait gallery comprising images of 87 persons.
It is widely recognized that visual experience plays an important role in the development of visu... more It is widely recognized that visual experience plays an important role in the development of visual capabilities in higher animals. It is also the experience of builders of machine vision systems that programming vision is hard and it would be nice for systems to do some of the work automatically through training. Learning is thus an important area of study
Knowledge Discovery and Data Mining, 1996
The unsupervised detection of hierarchical structuresis a major topic in unsupervised learning an... more The unsupervised detection of hierarchical structuresis a major topic in unsupervised learning and one ofthe key questions in data analysis and representation.We propose a novel algorithm for the problem of learningdecision trees for data clustering and related problems.In contrast to many other methods based onsuccessive tree growing and pruning, we propose anobjective function for tree evaluation and we derive anon--greedy
Neural Information Processing Systems, 2006
We show that the relevant information about a classification problem in feature space is containe... more We show that the relevant information about a classification problem in feature space is contained up to negligible error in a finite number of leading kernel PCA components if the kernel matches the underlying learning problem. Thus, ker- nels not only transform data sets such that good generalization can be achieved even by linear discriminant functions, but this transformation is
Pattern Recognition Letters, 1999
This paper introduces a novel statistical latent class model for probabilistic grouping of distri... more This paper introduces a novel statistical latent class model for probabilistic grouping of distributional and histogram data. Adopting the Bayesian framework, we propose to per- form annealed maximum a posteriori estimation to compute optimal clustering solutions. In order to accelerate the optimization process, an efficient multiscale formulation is devel- oped. We present a prototypical application of this method for unsupervised
Computer Vision and Pattern Recognition, 1997
In this paper we propose and examine non-parametric sta- tistical tests to define similarity and ... more In this paper we propose and examine non-parametric sta- tistical tests to define similarity and homogeneity measure s for textures. The statistical tests are applied to the coeffi- cients of images filtered by a multi-scale Gabor filter bank. We will demonstrate that these similarity measures are use- ful for both, texture based image retrieval and for unsuper- vised texture segmentation,
RHINO was the University of Bonn's entry in the 1994 AAAI Robot Competition and Exhibition. RHINO... more RHINO was the University of Bonn's entry in the 1994 AAAI Robot Competition and Exhibition. RHINO is a mobile robot designed for indoor navigation and manipulation tasks. The general scientific goal of the RHINO project is the development and the analysis of autonomous and complex learning systems. This paper briefly describes the major components of the RHINO control software as they were exhibited at the competition. It also sketches the basic philosophy of the RHINO architecture and discusses some of the lessons that we learned during the competition.
In this work we show that one can train Con- ditional Random Fields of intractable graphs eective... more In this work we show that one can train Con- ditional Random Fields of intractable graphs eectively and eciently by considering a mixture of random spanning trees of the un- derlying graphical model. Furthermore, we show how a maximum-likelihood estimator of such a training objective can subsequently be used for prediction on the full graph. We present experimental results which
IEEE Transactions on Pattern Analysis and Machine Intelligence - PAMI, 1997
Mass cytometry enables high-dimensional, single-cell analysis of cell type and state. In mass cyt... more Mass cytometry enables high-dimensional, single-cell analysis of cell type and state. In mass cytometry, rare earth metals are used as reporters on antibodies. Analysis of metal abundances using the mass cytometer allows determination of marker expression in individual cells. Mass cytometry has previously been applied only to cell suspensions. To gain spatial information, we have coupled immunohistochemical and immunocytochemical methods with high-resolution laser ablation to CyTOF mass cytometry. This approach enables the simultaneous imaging of 32 proteins and protein modifications at subcellular resolution; with the availability of additional isotopes, measurement of over 100 markers will be possible. We applied imaging mass cytometry to human breast cancer samples, allowing delineation of cell subpopulations and cell-cell interactions and highlighting tumor heterogeneity. Imaging mass cytometry complements existing imaging approaches. It will enable basic studies of tissue heterogeneity and function and support the transition of medicine toward individualized molecularly targeted diagnosis and therapies.
Künstliche Intelligenz - KI, 1998
Uploads
Papers by Joachim Buhmann