Wissenschaftliche Publikationen

Veröffentlichungen der HSWT

Die chronologische Liste zeigt aktuelle Veröffentlichungen aus dem Forschungsbetrieb der Hochschule Weihenstephan-Triesdorf. Zuständig ist das Zentrum für Forschung und Wissenstransfer (ZFW).

Suchbegriff

von

bis

Peer reviewed

Open access

8 Ergebnisse

Prof. Dr. Martin Stetter, Prof. Dr. Elmar W. Lang
Berechtigungen: Open Access

Berechtigungen: Peer Reviewed
Learning intuitive physics and one-shot imitation using state-action-prediction self-organizing maps (2021) Computational Intelligence and Neuroscience 2021 , S. 1-15. DOI: 10.1155/2021/5590445

Human learning and intelligence work differently from the supervised pattern recognition approach adopted in most deep learning architectures. Humans seem to learn rich representations by exploration and imitation, build causal models of the world, and use both to flexibly solve new tasks. We suggest a simple but effective unsupervised model which develops such characteristics. The agent learns to represent the dynamical physical properties of its environment by intrinsically motivated exploration and performs inference on this representation to reach goals. For this, a set of self-organizing maps which represent state-action pairs is combined with a causal model for sequence prediction. The proposed system is evaluated in the cartpole environment. After an initial phase of playful exploration, the agent can execute kinematic simulations of the environment’s future and use those for action planning. We demonstrate its performance on a set of several related, but different one-shot imitation tasks, which the agent flexibly solves in an active inference style.
Mehr
Dr. rer. nat. Thorsten Schön, Prof. Dr. Martin Stetter, O. Belova, A. Koch, Ana Maria Perfeito Tomé, Prof. Dr. Elmar W. Lang

Physarum Learner: A Slime Mold Inspired Structural Learning Approach (2016) A. Adamatzky (Hrsg.), Advances in Physarum Machines. Springer International , S. 489-519.
Dr. rer. nat. Thorsten Schön, Prof. Dr. Martin Stetter, Ana Maria Perfeito Tomé, Carlos García Puntonet, Prof. Dr. Elmar W. Lang
Berechtigungen: Peer Reviewed
Physarum Learner: A bio-inspired way of learning structure from data (2014) Expert Systems with Applications 41 (11), S. 5353-5370. DOI: 10.1016/j.eswa.2014.03.002
Dr. rer. nat. Thorsten Schön, Prof. Dr. Martin Stetter, Ana Maria Perfeito Tomé, Prof. Dr. Elmar W. Lang
Berechtigungen: Peer Reviewed
A new Physarum Learner for Network Structure Learning from Biomedical Data (2013) 6th International Conference on Bio-inspired Systems and Signal Processing (BIOSIGNALS 2013), 11.-14. Februar 2013, Barcelona .
Dr. rer. nat. Thorsten Schön, Prof. Dr. Martin Stetter, Prof. Dr. Elmar W. Lang
Berechtigungen: Peer Reviewed
Structure Learning for Bayesian Networks using the Physarum Solver (2012) 11th International Conference on Machine Learning and Applications (ICMLA 2012), 12.-15. Dezember 2012, Boca Raton . DOI: 10.1109/ICMLA.2012.89
Andreas Nägele, Mathäus Dejori, Prof. Dr. Martin Stetter

Robust Learning of High-dimensional Biological Networks with Bayesian Networks (2008) Schuster A. (eds) Robust Intelligent Systems. Springer, London , S. 139-161. DOI: 10.1007/978-1-84800-261-6_7
Prof. Dr. Martin Stetter, Linda Tambosi, Gustavo Deco

Verfahren zur rechnergestützten Verarbeitung von in einem Sensornetzwerk erfassten Messwerten (2008) German patent 10 2007 014 650 .
R. Schachtner, D. Lutter, P. Knollmüller, Ana Maria Perfeito Tomé, F. J. Theis, G. Schmitz, Prof. Dr. Martin Stetter, P. Gómez Vilda, Prof. Dr. Elmar W. Lang
Berechtigungen: Open Access

Berechtigungen: Peer Reviewed
Knowledge-based gene expression classification via matrix factorization (2008) Bioinformatics 24 (15), S. 1688-1697. DOI: 10.1093/bioinformatics/btn245

Seite von

Veröffentlichungen der HSWT

Learning intuitive physics and one-shot imitation using state-action-prediction self-organizing maps (2021) Computational Intelligence and Neuroscience 2021 , S. 1-15. DOI: 10.1155/2021/5590445

Physarum Learner: A Slime Mold Inspired Structural Learning Approach (2016) A. Adamatzky (Hrsg.), Advances in Physarum Machines. Springer International , S. 489-519.

Physarum Learner: A bio-inspired way of learning structure from data (2014) Expert Systems with Applications 41 (11), S. 5353-5370. DOI: 10.1016/j.eswa.2014.03.002

A new Physarum Learner for Network Structure Learning from Biomedical Data (2013) 6th International Conference on Bio-inspired Systems and Signal Processing (BIOSIGNALS 2013), 11.-14. Februar 2013, Barcelona .

Structure Learning for Bayesian Networks using the Physarum Solver (2012) 11th International Conference on Machine Learning and Applications (ICMLA 2012), 12.-15. Dezember 2012, Boca Raton . DOI: 10.1109/ICMLA.2012.89

Robust Learning of High-dimensional Biological Networks with Bayesian Networks (2008) Schuster A. (eds) Robust Intelligent Systems. Springer, London , S. 139-161. DOI: 10.1007/978-1-84800-261-6_7

Verfahren zur rechnergestützten Verarbeitung von in einem Sensornetzwerk erfassten Messwerten (2008) German patent 10 2007 014 650 .

Knowledge-based gene expression classification via matrix factorization (2008) Bioinformatics 24 (15), S. 1688-1697. DOI: 10.1093/bioinformatics/btn245

Betreuung der Publikationsseiten

Gerhard Radlmayr

Semiha Savas

Kontakt