SUMMARY OF JUERGEN SCHMIDHUBER'S PROFESSIONAL ACTIVITIES IN 2008 

PUBLICATIONS OF 2008 (published, accepted, invited, submitted - for pre-2008 articles, PDFs / HTMLs of printed publications, and overview links see http://www.idsia.ch/~juergen/onlinepub.html)

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. 

JOURNALS 2008
9. 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.
8. D. Ryabko and J. Schmidhuber. Using Data Compressors to Construct Order Tests for Homogeneity and Component Independence. Applied Mathematics Letters, 2008, in press.
7. F. Gomez, J. Schmidhuber, R. Miikkulainen. Accelerated Neural Evolution through Cooperatively Coevolved Synapses. Journal of Machine Learning Research (JMLR), 9:937-965, 2008.
6. J. Schmidhuber. Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes. Invited, 2008
5. J. Schmidhuber: Comparing the legacies of Gauss, Pasteur, Darwin. Nature, vol 452 p 530, 2008 (short correspondence).
4. J. Schmidhuber: The last inventor of the telephone. Science, 319, no. 5871 p. 1759, 2008 (short correspondence).
3. 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. 
2. On J. Schmidhuber's SNF grant 21-113364: D. Ryabko, M. Hutter. Predicting Non-Stationary Processes. Applied Mathematics Letters, 2008, in press. 
1. On J. Schmidhuber's SNF grant 21-113364: D. Ryabko, M. Hutter. On the Possibility of Learning in Reactive Environments with Arbitrary Dependence. Theoretical Computer Science, 2008, in press. 

CONFERENCES 2008
14. A. Graves, J. Schmidhuber. Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks. Proc. 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. Proc. NIPS'21, p 577-584, 2008, MIT Press, 2008.
12. J. Schmidhuber. Driven by Compression Progress. Proc. KES-2008, Lecture Notes in Computer Science LNCS 5177, p 11, Springer, 2008. (Abstract of invited keynote talk.)
11. T. Rueckstiess, M. Felder, J. Schmidhuber. State-Dependent Exploration for Policy Gradient Methods. Proc. 19th ECML, 2008.
10. J. Togelius, J. Schmidhuber. An Experiment in Automatic Game Design.  Proc. 2008 IEEE CIG-2008, Perth, Australia, 2008.
9. A. Agapitos, J. Togelius, S. Lucas, J. Schmidhuber. Generating Diverse Opponents with Multiobjective Evolution.  Proc. 2008 IEEE CIG-2008, Perth, Australia, 2008.
8. T. Schaul and J. Schmidhuber. A Scalable Neural Network Architecture for Board Games.  Proc. 2008 IEEE CIG-2008, Perth, Australia, 2008.
7. M. Gagliolo and J. Schmidhuber. Distributed Algorithm Portfolios. Proc. DCAI 2008
6. J. Togelius, T. Schaul, J. Schmidhuber, F. Gomez. Countering Poisonous Inputs with Memetic Neuroevolution.  Proc. PPSN-2008, Dortmund, 2008.
5. F. Sehnke, C. Osendorfer, T. Rueckstiess, A. Graves, J. Peters, and J. Schmidhuber. Policy gradients with parameter-based exploration for control. In Proc. ICANN-2008, Prague, LNCS 5163, p. 387-396. Springer, 2008.
4. D. Wierstra, T. Schaul, J. Peters, J. Schmidhuber. Episodic Reinforcement Learning by Logistic Reward-Weighted Regression. In Proc. ICANN-2008, Prague. Springer, 2008.
3. D. Wierstra, T. Schaul, J. Peters, J. Schmidhuber. Fitness Expectation Maximization. Proc. PPSN-2008, Dortmund, 2008.
2. D. Wierstra, T. Schaul, J. Peters, J. Schmidhuber. Natural Evolution Strategies. Proc. 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.

TEACHING 2008
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. 

HONORS 2008
Elected to the Academia Scientiarum et Artium Europaea, the European Academy of Sciences and Arts, whose ~ 1300 members include numerous Nobel laureates, renowned architects & artists, and Pope Benedict XVI 

NOMINATION 2008 ("Ruf")
for Full Professorship of Artificial Intelligence at Univ. Lugano, Switzerland

SELECTED INVITED TALKS 2008
6. 6 March 2009: Invited Keynote for Artificial General Intelligence AGI-09, on AI & Singularity. Washington DC
5. 19 Dec 2008: Plenary talk at "Art Meets Science" 2008
4. 10 Oct 2008: Invited Keynote for IEEE meeting on General AI cancelled
3. 5 Sep 2008: Invited Plenary Talk for ICANN 2008, Prague
2. 3 Sep 2008: Invited Keynote for Knowledge-Based and Intelligent Information & Engineering Systems KES 2008, Zagreb
1. 27 June 2008: Invited Keynote for Artificial Cognitive Systems 2008
Other: Additional invited talks at TUM, Univ. Zurich, ETH Zurich, Dagstuhl Castle, and others

EXTERNALLY FUNDED ONGOING PROJECTS / GRANTS 2008
5. EU project on natural & artificial fingers and machine learning
4. SNF project on theory & practice of reinforcement learning
3. SNF project on supervised recurrent networks 
2. External funding for research visits from abroad
1. Excellence Cluster Cognitive Technical Systems (CoTeSys)

PROJECTS STARTING IN 2009 (exchange rates as of March 2008)
9. EU project on developmental robotics and intrinsic motivations (~US$ 1.5m; total ~US$ 9m)
8. EU project on humanobs (~US$ 350k; total ~US$ 3m)
7. EU project on artificial hands with antagonistic & stiff muscles (~US$ 580k; total ~US$ 4.5m)
6. CTI project on handwriting recognition (~US$ 330k, with Luca Gambardella)
5. SNF project on supervised recurrent networks II (~US$ 340k)
4. SNF project on theory and practice of general methods for reinforcement learning (~US$ 425k)
3. Sinergia project on biologically plausible reinforcement learning (~US$ 280k; total ~US$ 1.4m)
2. ZSW project on predicting wind energy profitability with RNN (~US$ 200k). 
1. IGSSE project on physical cryptography (~US$ 200k)