Zur JKU Startseite
Institut für Machine Learning
Was ist das?

Institute, Schools und andere Einrichtungen oder Angebote haben einen Webauftritt mit eigenen Inhalten und Menüs.

Um die Navigation zu erleichtern, ist hier erkennbar, wo man sich gerade befindet.

Ältere Publikationen


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
Author(s): H. Bartsch - S. Hochreiter - K. Obermayer
Published: 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
Author(s): J. Schmidhuber - S. Hochreiter - Y. Bengio
Published: in A Field Guide to Dynamical Recurrent Networks, J. F. Kolen and S. C. Kremer (eds.), IEEE Press New York City, 2000, pp. 231-236
Download: PDF, öffnet eine externe URL in einem neuen Fenster
Gradient flow in recurrent nets: the difficulty of learning long-term dependencies Field Guide to Dynamical Recurrent Networks 2000
Author(s): S. Hochreiter - Y. Bengio - P. Frasconi - J. Schmidhuber
Published: in A Field Guide to Dynamical Recurrent Networks, J. F. Kolen and S. C. Kremer (eds.), IEEE Press New York City, 2000, pp. 237-244
Download: PDF, öffnet eine externe URL in einem neuen Fenster
An electric field approach to independent component analysis ICA 2000
Author(s): S. Hochreiter - M.C. Mozer
Published: Proceedings of the Second International Workshop on Independent Component Analysis and Blind Signal Separation, Helsinki, Finland, pp. 45-50, 2000
Download: PDF, öffnet eine externe URL in einem neuen Fenster
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