Sepp Hochreiter (born 1967 in Mühldorf am Inn) is a computer scientist working in the fields of bioinformatics and machine learning. Since 2006 he has been head of the Institute of Bioinformatics at the Johannes Kepler University of Linz. Before, he was at the Technical University of Berlin, at the University of Colorado at Boulder, and at the Technical University of Munich. He founded the Masters Program in Bioinformatics at the Johannes Kepler University of Linz where he is still the acting dean, he founded the Bioinformatics Working Group at the Austrian Computer Society, he is the representative of the University Linz at the Asea Uninet, he is founding board member of different bioinformatics start-up companies, he was program chair of the conference Bioinformatics Research and Development, he is editor, program committee member, and reviewer for international journals and conferences.
Contents |
Sepp Hochreiter developed "Factor Analysis for Robust Microarray Summarization" (FARMS).[1] FARMS has been designed for preprocessing and summarizing high-density oligonucleotide DNA microarrays at probe level to analyze RNA gene expression. FARMS is based on a factor analysis model which is optimized in a Bayesian framework by maximizing the posterior probability. On Affymetrix spiked-in and other benchmark data, FARMS outperformed all other methods. A highly relevant feature of FARMS is its informative/ non-informative (I/NI) calls.[2] The I/NI call is a Bayesian filtering technique which separates signal variance from noise variance. The I/NI call offers a solution to the main problem of high dimensionality when analyzing microarray data by selecting genes which are measured with high quality.[3][4] FARMS has been extended to cn.FARMS [5] for detecting DNA structural variants like copy number variations with a low false discovery rate.
Sepp Hochreiter developed "Factor Analysis for Bicluster Acquisition" (FABIA)[6] for biclustering that is simultaneously clustering rows and columns of a matrix. A bicluster in transcriptomic data is a pair of a gene set and a sample set for which the genes are similar to each other on the samples and vice versa. In drug design, for example, the effects of compounds may be similar only on a subgroup of genes. FABIA is a multiplicative model that assumes realistic non-Gaussian signal distributions with heavy tails and utilizes well understood model selection techniques like a variational approach in the Bayesian framework. FABIA supplies the information content of each bicluster to separate spurious biclusters from true biclusters.
Support vector machines (SVMs) are supervised learning methods used for classification and regression analysis by recognizing patterns and regularities in the data. Standard SVMs require a positive definite kernel to generate a squared kernel matrix from the data. Sepp Hochreiter proposed the "Potential Support Vector Machine" (PSVM),[7] which can be applied to non-square kernel matrices and can be used with kernels that are not positive definite. For PSVM model selection he developed an efficient sequential minimal optimization algorithm.[8] The PSVM minimizes a new objective which ensures theoretical bounds on the generalization error and automatically selects features which are used for classification or regression.
Sepp Hochreiter applied the PSVM to feature selection, especially to gene selection for microarray data.[9][10][11] The PSVM and standard support vector machines were applied to extract features that are indicative coiled coil oligomerization.[12]
Neural networks are different types of simplified mathematical models of biological neural networks like those in human brains. If data mining is based on neural networks, overfitting reduces the network's capability to correctly process future data. To avoid overfitting, Sepp Hochreiter developed algorithms for finding low complexity neural networks like "Flat Minimum Search" (FMS),[13] which searches for a "flat" minimum — a large connected region in the parameter space where the network function is constant. Thus, the network parameters can be given with low precision which means a low complex network that avoids overfitting.
Recurrent neural networks scan and process sequences and supply their results to the environment. Sepp Hochreiter developed the long short term memory,[14] which overcomes the problem of previous recurrent networks to forget information about the sequence which was observed at the begin of the sequence. LSTM learns from training sequences to solve numerous tasks like automatic music composition, speech recognition, reinforcement learning, and robotics. LSTM was successfully applied to very fast protein homology detection without requiring a sequence alignment.[15]