Cognitive Behavior of Humans, Animals, and Machines:
Situation Model Perspectives
Oktober 2019 – Juli 2020
Leitung: Werner Schneider (Bielefeld, GER), Helge Ritter (Bielefeld, GER)
Herbert Jaeger studied mathematics and psychology at the University of Freiburg and obtained his PhD in Computer Science (Artificial Intelligence) at the University of Bielefeld. After a 5-year postdoctoral fellowship at the German National Research Center for Computer Science (Sankt Augustin, Germany) he headed the "Intelligent Dynamical Systems" group at the Fraunhofer Institute for Autonomous Intelligent Systems AIS (Sankt Augustin, Germany). Since 2003 he is Associate Professor for Computational Science at Jacobs University Bremen. After August 2019 he will be Full Professor for Computing in Cognitive Materials at the Rijksuniversiteit Groningen.
Current Main Research Interests
Machine learning, especially with recurrent neural networks. Mathematical modeling of complex dynamical systems. Cognitive neural agent architectures. Theory of computing in non-digital hardware.
Five selected publications with particular relevance to the Research Group
- Jaeger, H. (2017). Using conceptors to manage neural long-term memories for temporal patterns. Journal of Machine Learning Research, 18, 1-43. http://jmlr.org/papers/v18/15-449.html
- Jaeger, H. (2014). Controlling recurrent neural networks by conceptors. Jacobs University technical report Nr 31. https://arxiv.org/abs/1403.3369
- Pascanu, R. & Jaeger, H. (2011). A neurodynamical model for working memory. Neural Networks, 24, 199-207.
- Jaeger, H. (1999). Action selection for delayed, stochastic reward. Proc. 4th Annual Conf. of the German Cognitive Science Society (KogWis99), Infix Verlag, 213-219.
- Jaeger, H. & Christaller, T. (1998). Dual dynamics: Designing behavior systems for autonomous robots. Artificial Life and Robotics, 2, 108-112.