Extraordinarius

Curriculum Vitæ

Jürgen Schmidhuber: 1963 born in Munich;1987 Diploma in computer science from TUM; 1991 PhD; 1991-93 postdoc at University of Colorado at Boulder, 1993 Habilitation at TUM. Since 1995 co-director of the Swiss AI lab IDSIA in Lugano, which he helped transform into one of the world's top 10 AI labs (the smallest!), according to Business Week (1997). Since 2003 Prof. SUPSI, Switzerland. Since 2004 Head of TUM Cogbotlab. 2004-2009 also Professor Extraordinarius of Cognitive Robotics in the Faculty of TUM Computer Science, working on robot learning. Since April 2009 Professor of Artificial Intelligence at the University of Lugano, Switzerland. Best known for his algorithms for learning programs running on recurrent neural networks (RNNs) and other computers (e.g., OOPS and GP), non-halting Turing machines and generalizations of Kolmogorov complexity, optimal universal learners, Goedel machines and earlier self-referential meta-learners, reinforcement learning, artificial evolution, non-linear ICA, artificial curiosity, a complexity-based theory of beauty, low-complexity art (a new minimal art form based on algorithmic information theory), the speed prior for optimal computable inductive inference in quickly computable universes, and an algorithmic theory of everything. Interested in statistical robotics, evolving RNNs for robot control, learning attentive vision, hierarchical learning, time series prediction, financial forecasting, robot cars, resilient machines with self-models, robot hands and arms with elastic tendons and muscles, artificial music composition, artificial ants, Fibonacci Web Design. He is promoting the New AI: general & sound & relevant for physics. Compare Schmidhuber's publications and motivation and deutsche Seite and check out what's new. Schmidhuber's computer science heroes: Schickard, Leibniz, Babbage, Goedel, Turing, Zuse. Compare Schmidhuber's law. Other scientists who left their mark: Gauss, Einstein, Haber & Bosch, Archimedes. Is history converging? Again?

---

Do you need us as German or Swiss partners for EU projects on cognitive systems, robot learning, time series analysis (call FP7 etc)? Contact us. BTW, is the EU a new kind of empire?

---

Dec 1 2009 is deadline for the conference on Artificial General Intelligence (AGI 2010) in Lugano, Switzerland! At the conference we'll also conduct additional job interviews for the remaining jobs announced below.

---

RECENT JOBS in Schmidhuber's Team at IDSIA in Switzerland (Nov 2009): Three postdocs of Schmidhuber just got professorships abroad. Now he is looking for three FRESH postdocs to replace them. More jobs: 5 Postdocs & 5 PhD students in Cognitive Robotics & Machine Learning (most of them filled now); 1 Postdoc and 1 PhD student in biologically plausible reinforcement learning; 2 Postdocs in handwriting recognition; 1 related Postdoc in medical image analysis; 1 PhD fellowship in evolutionary computation. More jobs at IDSIA.

Previous job ads (filled by now): 1. Machine Learning PostDoc. 2. Several Postdocs or PhD students (BAT IIa) for the new Excellence Cluster Cognitive Technical Systems (CoTeSys). Topics: Artificial curiosity for the DLR artificial hand, and behavior evolution for the AM 180cm biped. See the CoTeSys link. 3. Jobs at TUM (EU-Project).

---

LECTURES, SEMINARS, LAB COURSES

WS 2008/09: Course Machine Learning I, Hauptseminar Evolutionary Algorithms, Hauptseminar Sequence Learning
SS 2008: Course Machine Learning II, Machine Learning Lab Course, Hauptseminar Evolutionary Algorithms, Hauptseminar Reinforcement Learning, Hauptseminar Sequence Learning, Proseminar Musik und Informatik.
WS 2007/08: Course Machine Learning I, Proseminar Genetic Programming, Seminar Reinforcement Learning, Seminar Machine Learning and Computer Vision. The Praktikum Machine Learning Lab Course will be offered again next summer.
SS 2007: Course Machine Learning II, Machine Learning Lab Course, Proseminar Genetic Programming, Seminar Machine Learning and Computer Vision, Seminar Probabilistic Models of the Brain
WS 2006/07: Course Machine Learning 1, Machine Learning Lab Course, Proseminar Game Theory (2 groups), Proseminar Music and Computer Science, Seminar Machine Learning and Computer Vision, PhD student seminar, Sep 17-29: Sarntal Ferienakademie: Music & Machine Learning

---

SCHMIDHUBER'S TUM-TEAM ("DIE BUAM")
1. Christian Osendorfer
2. Thomas Rückstiess
3. Frank Sehnke
4. Dr. rer. nat. Martin Felder
5. Dr. rer. nat. Alex Graves
6. Alessandro Stranieri
7. Dr. rer. nat. Volker Baier (LMU)
8. Holger Urbanek (DLR)
9. Daniel Weiss
10. Justin Bayer
11. Andreas Häusler
12. Michael Isik
13. Ulrich Rührmair
Interacting with the IDSIA Team!

---

HONORS 2008
Elected to the Academia Scientiarum et Artium Europaea, the European Academy of Sciences and Arts, whose 1200 members include numerous Nobel laureates, renowned architects & artists, and Pope Benedict XVI

---

SELECTED INVITED TALKS 2008
6 March 2009: Invited Keynote for Artificial General Intelligence AGI-09, on AI & Singularity. Washington DC, USA
10 Oct 2008: Invited Keynote for IEEE meeting on General AI cancelled
5 Sep 2008: Invited Plenary Talk for ICANN 2008, Prague
3 Sep 2008: Invited Keynote for Knowledge-Based and Intelligent Information & Engineering Systems KES 2008, Zagreb
27 June 2008: Invited Keynote for Artificial Cognitive Systems, Munich
Additional invited talks at TUM, Univ. Zurich, ETH Zurich, Dagstuhl Castle, and others

SELECTED INVITED TALKS 2007
2 Oct: Joint Invited Lecture for Algorithmic Learning Theory (ALT 2007) and Discovery Science (DS 2007), Sendai, Japan: Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity.
22 Aug: Invited Plenary Talk at the A*STAR Meeting on Expectation & Surprise, Singapore: On Artificial Curiosity
12 July: Invited Plenary Address at "Art Meets Science 2007": Randomness vs simplicity & beauty in physics and the fine arts.
24 Apr: Invited Plenary Talk at ACAT'07 (Advanced Computing and Analysis Techniques in Physics Research), Amsterdam: How to learn a program.
Additional invited talks at Gatsby Neuroscience (UK), Reading Univ. (UK), Univ. Bochum, LMU Munich, BSI Riken (Japan), Univ. Tokyo, Univ. Hokkaido, Univ. Kyoto

---

SCIENTIFIC EVENTS ORGANIZED IN 2007
Co-Organizer of the European Land Robot Trials ELROB 2007, August 2007, Switzerland
Co-Organizer of the CoTeSys Workshop on Learning & Planning 2007
Co-Organizer of the NanoBioTact Workshop on Tactile Sensing 2007

---

Selected Publications 2007 / 2008

For pre-2007 articles, PDFs / HTMLs of printed publications, and overview links click here.

BOOKS 2008
J. Schmidhuber, F. Gomez, S. Fernandez, A. Graves, S. Hochreiter. Sequence Learning with Artificial Recurrent Neural Networks. (Aiming to become the definitive textbook on RNN.) Invited by Cambridge University Press, 2008, in preparation. We ask those who have contributed to the field to send additional relevant references - see the preliminary RNN book web site.

JOURNALS 2008
7. A. Graves, M. Liwicki, S. Fernandez, R. Bertolami, H. Bunke, J. Schmidhuber. A Novel Connectionist System for Improved Unconstrained Handwriting Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008.
6. D. Ryabko and J. Schmidhuber. Using Data Compressors to Construct Order Tests for Homogeneity and Component Independence. Applied Mathematics Letters, 2008, in press.
5. F. Gomez, J. Schmidhuber, R. Miikkulainen. Accelerated Neural Evolution through Cooperatively Coevolved Synapses. Journal of Machine Learning Research (JMLR), 9:937-965, 2008.
4. J. Schmidhuber. Simple Algorithmic Principles of Artificial Curiosity, Creativity, Attention, and Subjective Beauty. SICE Journal. Invited, 2008
3. J. Schmidhuber: Comparing the legacies of Gauss, Pasteur, Darwin. Nature, vol 452 p 530, 2008 (short correspondence).
2. J. Schmidhuber: The last inventor of the telephone. Science, 319, no. 5871 p. 1759, 2008 (short correspondence).
1. H. Mayer, F. Gomez, D. Wierstra, I. Nagy, A. Knoll, and J. Schmidhuber. A System for Robotic Heart Surgery that Learns to Tie Knots Using Recurrent Neural Networks. Advanced Robotics, 22/13-14, p. 1521-1537, 2008.

MORE JOURNALS ON SCHMIDHUBER'S GRANTS 2008
2. D. Ryabko, M. Hutter. Predicting Non-Stationary Processes. Applied Mathematics Letters, 2008, in press. (J. Schmidhuber's SNF grant 21-113364.)
1. D. Ryabko, M. Hutter. On the Possibility of Learning in Reactive Environments with Arbitrary Dependence. Theoretical Computer Science, 2008, in press. (J. Schmidhuber's SNF grant 21-113364.)

CONFERENCES 2008
14. A. Graves, J. Schmidhuber. Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks. Advances in Neural Information Processing Systems 22, NIPS'22, Vancouver, 2008, in press (to appear 2009).
13. A. Graves, S. Fernandez, M. Liwicki, H. Bunke, J. Schmidhuber. Unconstrained online handwriting recognition with recurrent neural networks. Advances in Neural Information Processing Systems 21, NIPS'21, p 577-584, 2008, MIT Press, Cambridge, MA, 2008.
12. J. Schmidhuber. Driven by Compression Progress. In Knowledge-Based Intelligent Information and Engineering Systems KES-2008, Lecture Notes in Computer Science LNCS 5177, p 11, Springer, 2008. (Abstract of invited keynote.)
11. T. Rückstiess, M. Felder, J. Schmidhuber. State-Dependent Exploration for Policy Gradient Methods. 19th European Conference on Machine Learning ECML, 2008.
10. J. Togelius, J. Schmidhuber. An Experiment in Automatic Game Design Proceedings of the 2008 IEEE Symposium on Computational Intelligence in Games CIG-2008, Perth, Australia, 2008.
9. A. Agapitos, J. Togelius, S. Lucas, J. Schmidhuber Generating Diverse Opponents with Multiobjective Evolution. Proceedings of the 2008 IEEE Symposium on Computational Intelligence in Games CIG-2008, Perth, Australia, 2008.
8. T. Schaul and J. Schmidhuber. A Scalable Neural Network Architecture for Board Games. Proceedings of the 2008 IEEE Symposium on Computational Intelligence in Games CIG-2008, Perth, Australia, 2008.
7. M. Gagliolo and J. Schmidhuber. Distributed Algorithm Portfolios. International Symposium on Distributed Computing and Artificial Intelligence 2008, DCAI 2008
6. J. Togelius, T. Schaul, J. Schmidhuber, F. Gomez. Countering Poisonous Inputs with Memetic Neuroevolution. Proceedings of Parallel Problem Solving from Nature PPSN-2008, Dortmund, 2008.
5. F. Sehnke, C. Osendorfer, T. Rückstiess, A. Graves, J. Peters, and J. Schmidhuber. Policy gradients with parameter-based exploration for control. In Proceedings of the International Conference on Artificial Neural Networks ICANN-2008, Prague, LNCS 5163, pages 387-396. Springer-Verlag Berlin Heidelberg, 2008.
4. D. Wierstra, T. Schaul, J. Peters, J. Schmidhuber. Episodic Reinforcement Learning by Logistic Reward-Weighted Regression. In Proceedings of the International Conference on Artificial Neural Networks ICANN-2008, Prague. Springer-Verlag Berlin Heidelberg, 2008.
3. D. Wierstra, T. Schaul, J. Peters, J. Schmidhuber. Fitness Expectation Maximization. Proceedings of Parallel Problem Solving from Nature PPSN-2008, Dortmund, 2008.
2. D. Wierstra, T. Schaul, J. Peters, J. Schmidhuber. Natural Evolution Strategies. Proceedings of IEEE Congress on Evolutionary Computation CEC-2008, Hongkong, 2008.
1. J. Togelius, F. Gomez, J. Schmidhuber. Learning What to Ignore: Memetic Climbing in Topology and Weight Space. IEEE WCCI 2008, Hong Kong, 2008.

JOURNALS 2007
5. J. Schmidhuber. Alle berechenbaren Universen. Spektrum der Wissenschaft (German edition of Scientific American), 2007
4. J. Schmidhuber, D. Wierstra, M. Gagliolo, F. Gomez. Training Recurrent Networks by Evolino. Neural Computation, 19(3): 757-779, 2007
3. A. Chernov, M. Hutter, J. Schmidhuber. Algorithmic Complexity Bounds on Future Prediction Errors. Information and Computation 205(2):242-261, 2007
2. J. Schmidhuber: Prototype Resilient, Self-Modeling Robots. Science, 316, no. 5825 p 688, 2007 (short correspondence)
1. M. Gagliolo, J. Schmidhuber: Learning Dynamic Algorithm Portfolios. Annals of Mathematics and Artificial Intelligence (2006) 47:295-328, doi 10.1007/s10472-006-9036-z, published online January 2007

MORE JOURNALS ON SCHMIDHUBER'S GRANTS 2007
2. I. N. Athanasiadis. The Fuzzy Lattice Reasoning Classifier for mining environmental data. Studies in Computational Intelligence, 67:175-193, 2007. (J. Schmidhuber's SNF grant 21-113364.)
1. V. G. Kaburlasos, I. N. Athanasiadis, and P. A. Mitkas. Fuzzy Lattice Reasoning (FLR) classifier and its application for ambient ozone estimation. International Journal of Approximate Reasoning, 45(1):152-188, 2007. (J. Schmidhuber's SNF grant 21-113364.)

INVITED BOOK CHAPTERS 2007
2. J. Schmidhuber. Celebrating 75 years of AI - History and Outlook: the Next 25 Years. Proc. 50th Anniversary of AI, LNAI, Springer, 2007, in press
1. J. Schmidhuber. New Millennium AI. In W. Duch and J. Mandziuk, eds., Challenges to Computational Intelligence, p 15-36, Studies in Computational Intelligence, vol. 63, Springer-Verlag, 2007. Preprint: arXiv:cs.AI/0606081

CONFERENCES 2007
11. J. Schmidhuber. Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity. In V. Corruble, M. Takeda, E. Suzuki, eds., Proc. 10th Intl. Conf. on Discovery Science (DS 2007) p. 26-38, LNAI 4755, Springer, 2007. Joint invited lecture for DS 2007 and ALT 2007, Sendai, Japan, 2007. Preprint: arxiv:0709.0674
10. J. Schmidhuber (see #11 above): Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity. M. Hutter, R. A. Servedio, E. Takimoto, eds., Proc. 18th Intl. Conf. on Algorithmic Learning Theory (ALT 2007) p. 32, LNAI 4754, Springer, 2007. Joint invited lecture for ALT 2007 and DS 2007
9. A. Graves, S. Fernandez, J. Schmidhuber. Unconstrained online handwriting recognition with recurrent neural networks. Advances in Neural Information Processing Systems 21, NIPS'21, Vancouver, 2007, in press
8. D. Wierstra, J. Schmidhuber. Policy Gradient Critics. 18th European Conference on Machine Learning ECML, Warszaw, 2007
7. M. Liwicki, A. Graves, H. Bunke, J. Schmidhuber. A novel approach to on-line handwriting recognition based on bidirectional long short-term memory networks. 9th International Conference on Document Analysis and Recognition, 2007
6. S. Fernandez, A. Graves, J. Schmidhuber. An application of recurrent neural networks to discriminative keyword spotting. Intl. Conf. on Artificial Neural Networks ICANN'07, 2007
5. A. Graves, S. Fernandez, J. Schmidhuber. Multi-Dimensional Recurrent Neural Networks. Intl. Conf. on Artificial Neural Networks ICANN'07, 2007
4. D. Wierstra, A. Foerster, J. Schmidhuber. Solving Deep Memory POMDPs with Recurrent Policy Gradients. Intl. Conf. on Artificial Neural Networks ICANN'07, 2007
3. A. Foerster, A. Graves, J. Schmidhuber. RNN-based Learning of Compact Maps for Efficient Robot Localization. 15th European Symposium on Artificial Neural Networks, ESANN, Bruges, Belgium, 2007
2. S. Fernandez, A. Graves, J. Schmidhuber. Sequence labelling in structured domains with hierarchical recurrent neural networks. In Proc. 20th International Joint Conference on Artificial Intelligence (IJCAI 07), p. 774-779, Hyderabad, India, 2007 (talk)
1. M. Gagliolo and J. Schmidhuber. Learning restart strategies. In M. M. Veloso, ed., Proc. 20th International Joint Conference on Artificial Intelligence (IJCAI 07), p. 792-797, Hyderabad, India, AAAI Press, 2007 (talk)
ACCEPTANCE RATES where known: IJCAI: 15% (two talks), NIPS: 25%, ECML: 21%