Classification, Regression, and Feature Selection on Matrix Data _{Tech. Report 2004}

Gene Selection for Microarray Data _{Kernel Methods in Computational Biology 2004}

Learning quadratic forms by density estimation and its application to image coding _{Neurocomputing 2004}

Classification and Feature Selection on Matrix Data with Application to Gene-Expression Analysis _ISI 2003

Gene Selection with Support Vector Machines _{Workshop Kernel Methods in Computational Biology 2003}

Learning Quadratic Forms by Density Estimation and its Application to Image Coding _CNS 2003

Feature Selection and Classification on Matrix Data: From Large Margins To Small Covering Numbers _NIPS 2003

Coulomb Classifiers: Generalizing Support Vector Machines via an Analogy to Electrostatic Systems _NIPS 2003

Classification of Pairwise Proximity Data with Support Vectors _{The Learning Workshop 2002}

Coulomb Classifiers: Reinterpreting SVMs as Electrostatic Systems _{Tech. Report 2001}

Monaural separation and classification of non-linear transformed and mixed independent signals: An SVM perspective _ICA 2001

Learning to Learn Using Gradient Descent _ICANN 2001

A Discrete Probabilistic Memory Model for Discovering Dependencies in Time _ICANN 2001

Meta-Learning with Backpropagation _{IEEE Neural Networks 2001}

Beyond maximum likelihood and density estimation: A sample-based criterion for unsupervised learning of complex models _NIPS 2001

Evaluating benchmark problems by random guessing _{Field Guide to Dynamical Recurrent Networks 2000}

Gradient flow in recurrent nets: the difficulty of learning long-term dependencies _{Field Guide to Dynamical Recurrent Networks 2000}

An electric field approach to independent component analysis _ICA 2000

Nonlinear ICA through low-complexity autoencoders _{IEEE Circuits and Systems 1999}

LOCOCODE performs nonlinear ICA without knowing the number of sources _ICA 1999

Feature extraction through LOCOCODE _{Neural Computation 1999}

Source Separation as a By-product of Regularization _{NIPS 1999}

The vanishing gradient problem during learning recurrent neural nets and problem solutions _{Journal of Uncertainty 1998}

LOCOCODE versus PCA and ICA _{ICANN 1998}

LOCOCODE _{Tech. Report 1997}

Long Short-Term Memory _{Neural Computation 1997}

Low-complexity coding and decoding _{TANC 1997}

Unsupervised coding with Lococode _{ICANN 1997}

Recurrent Neural Net Learning and Vanishing Gradient _{Fuzzy-Neuro Workshop 1997}

LSTM can solve hard long time lag problems _{NIPS 1997}

Bridging Long Time Lags by Weight Guessing and Long Short-Term Memory _{Spatiotemporal models in biological and artificial systems 1996}

Guessing can outperform many long time lag algorithms _{Tech. Note 1996}

Flat minima _{Tech. Report 1995}

Reinforcement driven information acquisition in non-deterministic environments _{ICANN 1995}

Long short term memory _{Tech. Report 1995}

Simplifying nets by discovering flat minima _{NIPS 1995}

Flat minimum search finds simple nets _{Tech. Report 1994}

Untersuchungen zu dynamischen neuronalen Netzen _{Diploma Thesis 1991}

Implementierung und Anwendung eines ‘neuronalen’ Echtzeit-Lernalgorithmus für reaktive Umgebungen _{Prac. Work 1990}