Juergen Schmidhuber's online publications

JÜRGEN SCHMIDHUBER'S PUBLICATIONS

Many of the downloadable files below are in HTML or PDF format. But some are postscripts or gzipped postscripts; decompress them with "gunzip". For bibtex entries see Schmidhuber's unordered bibfile (includes stuff he cited).

OVERVIEW PAGES BY TOPIC

Feedback Neural Networks (1989-2009)
Gödel machines (2003-2009)
Optimal Ordered Problem Solver (2002-2004)
Learning Robots (2002-2009)
Evolution (1987-2009)
Universal AI (2000-2009)
Reinforcement learning (RL) (1989-2009)
Subgoal learning & Hierarchical RL (1990-2009)
Artificial Curiosity & Creativity & Intrinsic Motivation & Developmental Robotics (1990-2009)
Theory of Beauty (1994-2009)
Computable universes / generalized algorithmic information (1997-2007)

BOOKS & THESES

4. 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, in preparation. See the preliminary RNN book web site.

3. J. Schmidhuber. Netzwerkarchitekturen, Zielfunktionen und Kettenregel (Network architectures, objective functions, and chain rule). Habilitation (postdoctoral thesis - qualification for a tenure professorship), Institut für Informatik, Technische Universität München, 1993 (496 K). PDF . HTML.

2. J. Schmidhuber. Dynamische neuronale Netze und das fundamentale raumzeitliche Lernproblem (Dynamic neural nets and the fundamental spatio-temporal credit assignment problem). Dissertation, Institut für Informatik, Technische Universität München, 1990. PDF . HTML.

1. J. Schmidhuber. Evolutionary principles in self-referential learning, or on learning how to learn: The meta-meta-... hook. Diploma thesis, Institut für Informatik, Technische Universität München, 1987. HTML.

JOURNALS

Journal impact factors may be ``the poor man's citation analysis'' according to A. van Raan, Nature 415:6873, Feb 2002. Pages 726-732 of Nature's issue point out flaws of ISI's citation counts, which favor reviews over original work, do not measure quality but a particular form of short-term impact, systematically underestimate non-mainstream papers that are ahead of time (with delayed impact) as well as papers of authors with strange names, etc. Having said this, according to the Journal Citation Reports ratings, during the time when most of the papers below were published, the top seven journals in the area COMPUTER SCIENCE/ARTIFICIAL INTELLIGENCE were: 1. Neural Computation (a dozen papers in the list below), 2. IEEE Trans. Pattern. Analysis, 3. IEEE Trans. Neural Networks, 4. Artificial Intelligence, 5. Neural Networks, 6. Cognitive Brain Research, 7. Machine Learning.

Short correspondence to Nature and Science (on the history of tech & science)
7. J. Schmidhuber: Comparing the legacies of Gauss, Pasteur, Darwin (Nature vol 452, p 530, April 2008)
6. J. Schmidhuber: The last inventor of the telephone. (Science 319, no. 5871, p. 1759, March 2008)
5. J. Schmidhuber: Prototype resilient, self-modeling robots (Science 316, no. 5825 p 688, May 2007)
4. J. Schmidhuber: Colossus was the first electronic digital computer (Nature 441 p 25, May 2006)
3. J. Schmidhuber: Randomness in physics (Nature 439 p 392, Jan 2006)
2. J. Schmidhuber: Turing's impact (Nature 429 p 501, June 2004)
1. J. Schmidhuber: First Pow(d)ered flight / plane truth (Nature 421 p 689, Feb 2003)

48. T. Schaul, J. Bayer, D. Wierstra, S. Yi, M. Felder, F. Sehnke, T. Rückstiess, J. Schmidhuber. PyBrain. Journal of Machine Learning Research, 2010, in press. PDF.

47. F. Sehnke, C. Osendorfer, T. Rückstiess, A. Graves, J. Peters, J. Schmidhuber. Parameter-exploring policy gradients. Neural Networks 23(2), 2010, in press.

46. J. Schmidhuber. Ultimate Cognition à la Gödel. Cognitive Computation 1(2):177-193, 2009. PDF. (Springer.)

45. J. Schmidhuber. Simple Algorithmic Theory of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes. Journal of SICE, 48(1):21-32, 2009. PDF.
Extended version (2008, revised 2009): arXiv:0812.4360; PDF (Dec 2008); PDF (April 2009).

44. D. Ryabko and J. Schmidhuber. Using Data Compressors to Construct Order Tests for Homogeneity and Component Independence. Applied Mathematics Letters, 2009. arXiv:0709.0670

43. 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, vol. 31, no. 5, 2009. PDF.

42. D. Wierstra, A. Foerster, J. Peters, J. Schmidhuber. Recurrent Policy Gradients. Journal of Algorithms, 2009. PDF.

41. J. Togelius, T. Schaul, D. Wierstra, C. Igel, F. Gomez, J. Schmidhuber. Ontogenetic and Phylogenetic Reinforcement Learning. Kuenstliche Intelligenz, 2009. PDF.

40. F. Gomez, J. Schmidhuber, R. Miikkulainen. Accelerated Neural Evolution through Cooperatively Coevolved Synapses. Journal of Machine Learning Research (JMLR), 9:937-965, 2008. PDF.

39. 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.

38. J. Schmidhuber. Alle berechenbaren Universen. (All computable universes.) Spektrum der Wissenschaft (German edition of Scientific American), 2007, Spezial 3/07, p. 75-79, 2007. PDF.

37. J. Schmidhuber, D. Wierstra, M. Gagliolo, F. Gomez. Training Recurrent Networks by Evolino. Neural Computation, 19(3): 757-779, 2007. PDF (preprint). Compare Evolino overview.

36. 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. Abstract. PDF (11MB).

35. A. Chernov, M. Hutter, J. Schmidhuber. Algorithmic Complexity Bounds on Future Prediction Errors. Information and Computation, 205(2):242-261, 2007. PDF.

34. J. Schmidhuber. Developmental Robotics, Optimal Artificial Curiosity, Creativity, Music, and the Fine Arts. Connection Science, 18(2): 173-187, June 2006. PDF.

33. J. Schmidhuber. The Computational Universe. Review of Programming the Universe: A Quantum Computer Scientist Takes on the Cosmos, by Seth Lloyd. American Scientist, July-August 2006. HTML.

32. A. Graves and J. Schmidhuber. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Networks, 18:5-6, pp. 602-610, 2005. PDF.

31. J. Schmidhuber. Optimal Ordered Problem Solver. Machine Learning, 54, 211-254, 2004. PDF. HTML. HTML overview.

30. M. Milano, P. Koumoutsakos, J. Schmidhuber. Self-Organizing Nets for Optimization. IEEE Transactions on Neural Networks, 15(3):758-765, 2004. PDF.

29. J. A. Perez-Ortiz, F. A. Gers, D. Eck, J. Schmidhuber. Kalman filters improve LSTM network performance in problems unsolvable by traditional recurrent nets. Neural Networks 16(2):241-250, 2003. PDF.

28. J. Schmidhuber. Hierarchies of generalized Kolmogorov complexities and nonenumerable universal measures computable in the limit. International Journal of Foundations of Computer Science 13(4):587-612, 2002. PDF. Based on sections 2-5 of: Algorithmic theories of everything (PDF, HTML) (2000, 515K, 50 pages, 10 theorems, 100 refs), also in the physics archive http://arXiv.org/abs/quant-ph/0011122 . HTML overview and flawed HTML (knowledge of LATEX helps).

27. F. Gers, N. Schraudolph, J. Schmidhuber. Learning precise timing with LSTM recurrent networks. Journal of Machine Learning Research 3:115-143, 2002. PDF.

26. J. Schmidhuber, F. Gers, D. Eck. Learning nonregular languages: A comparison of simple recurrent networks and LSTM. Neural Computation, 14(9):2039-2041, 2002. PDF.

25. I. W. Kwee and J. Schmidhuber. Optimal control using the transport equation: The Liouville Machine. Adaptive Behavior, 9(2):105-118, 2002.

24. F. A. Gers and J. Schmidhuber. LSTM Recurrent Networks Learn Simple Context Free and Context Sensitive Languages. IEEE Transactions on Neural Networks 12(6):1333-1340, 2001. PDF.

23. F. A. Gers and J. Schmidhuber and F. Cummins. Learning to Forget: Continual Prediction with LSTM. Neural Computation, 12(10):2451--2471, 2000. PDF.

22. N. N. Schraudolph, M. Eldracher, J. Schmidhuber. Processing Images by Semi-Linear Predictability Minimization. Network, 10(2): 133-169, 1999 (1766 K). PDF .

21. M. Wiering, R. Salustowicz, J. Schmidhuber. Reinforcement learning soccer teams with incomplete world models. Journal of Autonomous Robots, 7(1):77-88, 1999. PDF .

20. S. Hochreiter and J. Schmidhuber. Feature extraction through LOCOCODE. (28 pages, 20 figures, 703 K, 4.9 M gunzipped). PDF . HTML (some pictures missing). Neural Computation 11(3): 679-714, 1999

19. M. Wiering and J. Schmidhuber. Fast online Q(lambda). Machine Learning, 33(1), 105-116, 1998 (80 K). PDF .

18. R. Salustowicz and M. Wiering and J. Schmidhuber. Learning team strategies: soccer case studies. Machine Learning 33(2/3), 263-282, 1998 (127 K). PDF .

17. M. Wiering and J. Schmidhuber. HQ-Learning . Adaptive Behavior 6(2):219-246, 1997 (122 K). PDF . HTML.

16. J. Schmidhuber, J. Zhao, and M. Wiering. Shifting inductive bias with success-story algorithm, adaptive Levin search, and incremental self-improvement. Machine Learning 28:105-130, 1997. PDF . Flawed HTML.

15. R. Salustowicz and J. Schmidhuber. Probabilistic incremental program evolution. Evolutionary Computation, 5(2):123-141, 1997. PDF.

14. S. Hochreiter and J. Schmidhuber. Long Short-Term Memory. Neural Computation, 9(8):1735-1780, 1997 (170 K). PDF . Led to a lot of follow-up work.

13. J. Schmidhuber. Discovering neural nets with low Kolmogorov complexity and high generalization capability. Neural Networks, 10(5):857-873, 1997 (123 K). PDF , HTML

12. J. Schmidhuber. Low-Complexity Art. Leonardo, Journal of the International Society for the Arts, Sciences, and Technology, 30(2):97-103, MIT Press, 1997. Print on high-resolution (600 dpi) printer, preferrably double paged on A4 paper (172 K, uncompresses to 1.1 M). PDF. HTML.

11. S. Hochreiter and J. Schmidhuber. Flat Minima. Neural Computation, 9(1):1-42, 1997, (201 K). HTML.

10. J. Schmidhuber and M. Eldracher and B. Foltin. Semilinear predictability minimzation produces well-known feature detectors. Neural Computation, 8(4):773-786, 1996 (260 K). PDF . HTML.

9. J. Schmidhuber and S. Heil. Sequential neural text compression. IEEE Transactions on Neural Networks, 7(1):142-146, 1996 (68 K). PDF. HTML.

8. J. Schmidhuber and D. Prelinger. Discovering predictable classifications. Neural Computation, 5(4):625-635, 1993 (51 K). PDF. HTML.

7. J. Schmidhuber. Learning factorial codes by predictability minimization. Neural Computation, 4(6):863-879, 1992 (53 K). PDF. HTML.

6. J. Schmidhuber. Learning complex, extended sequences using the principle of history compression. Neural Computation, 4(2):234-242, 1992 (41 K). PDF. HTML.

5. J. Schmidhuber. A fixed size storage O(n^3) time complexity learning algorithm for fully recurrent continually running networks. Neural Computation, 4(2):243-248, 1992 (33 K). PDF. HTML.

4. J. Schmidhuber. Learning to control fast-weight memories: An alternative to recurrent nets. Neural Computation, 4(1):131-139, 1992 (39 K). PDF. HTML. Pictures (German).

3. J. Schmidhuber and R. Huber. Learning to generate artificial fovea trajectories for target detection. International Journal of Neural Systems, 2(1 & 2):135-141, 1991 (50 K - figures omitted!). PDF . HTML. HTML overview with pictures.

2. J. Schmidhuber. Additional remarks on G. Lukes' review of Schmidhuber's paper `Recurrent networks adjusted by adaptive critics'. Neural Network Reviews, 4(1):43, 1990.

1. J. Schmidhuber. A local learning algorithm for dynamic feedforward and recurrent networks. Connection Science, 1(4):403-412, 1989. (The Neural Bucket Brigade - figures omitted!). PDF. HTML.

INVITED BOOK CHAPTERS

18. J. Schmidhuber. Art & science as by-products of the search for novel patterns, or data compressible in unknown yet learnable ways. In M. Botta (ed.), Multiple ways to design research. Research cases that reshape the design discipline, Milano-Lugano, Swiss Design Network - Et al. Edizioni, 2009, pp. 98-112. (Keynote talk.) PDF of preprint.

17. 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. Based on keynote talk for KES 2008 (below) and joint invited lecture for ALT 2007 / DS 2007 (below). In G. Pezzulo, M. V. Butz, O. Sigaud, G. Baldassarre, eds.: Anticipatory Behavior in Adaptive Learning Systems, from Sensorimotor to Higher-level Cognitive Capabilities, Springer, LNAI, 2009, in press. Preprint (2008, revised 2009): arXiv:0812.4360. PDF (Dec 2008). PDF (April 2009).

16. J. Schmidhuber. Celebrating 75 years of AI - History and Outlook: the Next 25 Years. In Proc. 50th Anniversary of AI, p. 29-41, LNAI 4850, Springer, 2007. Preprint: arxiv:0798.4311.

15. J. Schmidhuber. New Millennium AI. In W. Duch and J. Mandziuk, eds., Challenges to Computational Intelligence, 2006. Preprint: arxiv:cs/0606081, 19 June 2006.

14. J. Schmidhuber. Goedel machines: Fully Self-Referential Optimal Universal Self-Improvers. In B. Goertzel and C. Pennachin, eds.: Artificial General Intelligence, p. 199-226, 2006. PDF.

13. J. Schmidhuber. The New AI: General & Sound & Relevant for Physics (HTML). TR IDSIA-04-03. In B. Goertzel and C. Pennachin, eds.: Artificial General Intelligence, p. 175-198, 2006. PDF.

12. J. Schmidhuber. Goedel machines: Towards a Technical Justification of Consciousness. In D. Kudenko, D. Kazakov, and E. Alonso, eds.: Adaptive Agents and Multi-Agent Systems III LNCS 3394, p. 1-23, Springer, 2005. PDF.

11. J. Schmidhuber. Exploring the Predictable. In Ghosh, S. Tsutsui, eds., Advances in Evolutionary Computing, p. 579-612, Springer, 2002. PDF . HTML.

10. M. Wiering, R. Salustowicz, J. Schmidhuber. Model-based reinforcement learning for evolving soccer strategies. In Computational Intelligence in Games, chapter 5. Editors N. Baba and L. Jain. pp. 99-131, 2001. PDF .

9. J. Schmidhuber. Sequential decision making based on direct search. In R. Sun and C. L. Giles, eds., Sequence Learning: Paradigms, Algorithms, and Applications. Lecture Notes on AI 1828, p. 203-240, Springer, 2001. PDF . HTML.

8. J. Schmidhuber, S. Hochreiter, Y. Bengio. Evaluating benchmark problems by random guessing. In S. C. Kremer and J. F. Kolen, eds., A Field Guide to Dynamical Recurrent Neural Networks. IEEE press, 2001. PDF . HTML.

7. S. Hochreiter, Y. Bengio, P. Frasconi, J. Schmidhuber. Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. In S. C. Kremer and J. F. Kolen, eds., A Field Guide to Dynamical Recurrent Neural Networks. IEEE press, 2001. PDF . HTML.

6. J. Schmidhuber and S. Heil. Compressing texts with neural nets. In Dale, Moisl and Somers, eds., Handbook of Natural Language Processing, pp. 863-872, Marcel Dekker, Inc., 2000. PDF . HTML.

5. R. Salustowicz and J. Schmidhuber. From Probabilities to Programs with Probabilistic Incremental Program Evolution. In D. Corne and M. Dorigo and F. Glover, eds., New Ideas in Optimization, p. 433-450, McGraw-Hill, London, 1999.

4. J. Schmidhuber. Neural predictors for detecting and removing redundant information. In H. Cruse, J. Dean, and H. Ritter, editors, Adaptive Behavior and Learning. Kluwer, 1999. PDF . HTML.

3. J. Schmidhuber. A general method for incremental self-improvement and multiagent learning. In X. Yao, editor, Evolutionary Computation: Theory and Applications. Chapter 3, pp.81-123, Scientific Publ. Co., Singapore, 1999 (submitted 1996). PDF . HTML.

2. J. Schmidhuber. A computer scientist's view of life, the universe, and everything. In C. Freksa, M. Jantzen, and R. Valk, eds., Foundations of Computer Science: Potential - Theory - Cognition, Lecture Notes in Computer Science, pages 201-208, Springer, 1997. PDF. HTML.

1. J. Schmidhuber, J. Zhao, N. Schraudolph. Reinforcement learning with self-modifying policies. In S. Thrun and L. Pratt, eds., Learning to learn, Kluwer, pages 293-309, 1997. Postscript; PDF; HTML.

CONFERENCES & WORKSHOPS

Some conferences accept less than 20% of the submitted papers, e.g., ECML 2004 or IJCAI 2005. Some accept around 25%, e.g., NIPS and ICML. On the other hand, the acceptance rate of any given conference does not necessarily say something about its quality: certain theoretically oriented conferences such as COLT (closer to 50%) receive comparatively few submissions, but most of them with high quality.

143. S. Yi, D. Wierstra, T. Schaul, J. Schmidhuber. Efficient Natural Evolution Strategies. Genetic and Evolutionary Computation Conference (GECCO-09), Montreal, 2009. PDF. Best paper award.

142. S. Yi, D. Wierstra, T. Schaul, J. Schmidhuber. Stochastic Search using the Natural Gradient. Proceedings of the 26th International Conference on Machine Learning (ICML-09), Montreal, 2009. PDF.

141. A. Graves, J. Schmidhuber. Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks. Advances in Neural Information Processing Systems 22, NIPS'22, p 545-552, Vancouver, MIT Press, 2009. PDF.

140. J. Bayer, D. Wierstra, J. Togelius, J. Schmidhuber. Evolving memory cell structures for sequence learning. Proceedings of the 19th International Conference on Artificial Neural Networks (ICANN-09), Cyprus, 2009. PDF.

139. J. Unkelbach, S. Yi, J. Schmidhuber. An EM based training algorithm for recurrent neural networks. Proceedings of the 19th International Conference on Artificial Neural Networks (ICANN-09), Cyprus, 2009. PDF.

138. F. J. Gomez, J. Togelius, J. Schmidhuber. Measuring and Optimizing Behavioral Complexity for Evolutionary Reinforcement Learning . Proceedings of the 19th International Conference on Artificial Neural Networks (ICANN-09), Cyprus, 2009. PDF.

137. T. Schaul and J. Schmidhuber. A Scalable Neural Network Architecture for Board Games. Proceedings of the 19th International Conference on Artificial Neural Networks (ICANN-09), Cyprus, 2009. PDF.

136. N. v. Hoorn, J. Togelius, J. Schmidhuber. Hierarchical Controller Learning in a First-Person Shooter. Proceedings of the 2009 IEEE Symposium on Computational Intelligence in Games, CIG-2009, p. 294-301, Milano, 2009. PDF.

135. J. Togelius, S. Karakovskiy, J. Koutnik, and J. Schmidhuber. Super Mario Evolution. Proceedings of the 2009 IEEE Symposium on Computational Intelligence in Games CIG-2009, p. 156-161, Milano, 2009. PDF.

134. N. van Hoorn, J. Togelius, D. Wierstra, J. Schmidhuber. Robust player imitation using multiobjective evolution. Proceedings of the Congress on Evolutionary Computation (CEC-09), Trondheim, 2009. PDF.

133. 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. PDF.

132. 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 talk.) PDF.

131. T. Rückstiess, M. Felder, J. Schmidhuber. State-Dependent Exploration for Policy Gradient Methods. 19th European Conference on Machine Learning ECML, 2008. PDF.

130. 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.

129. 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.

128. 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. PDF.

127. M. Gagliolo and J. Schmidhuber. Distributed Algorithm Portfolios. International Symposium on Distributed Computing and Artificial Intelligence 2008 , DCAI 2008

126. 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. PDF.

125. F. Sehnke, C. Osendorfer, T. Rückstiess, A. Graves, J. Peters, and J. Schmidhuber. Policy gradients with parameter-based exploration for control. In J. Koutnik V. Kurkova, R. Neruda, editors, Proceedings of the International Conference on Artificial Neural Networks ICANN-2008 ICANN 2008, Prague, LNCS 5163, pages 387-396. Springer-Verlag Berlin Heidelberg, 2008. PDF.

124. D. Wierstra, T. Schaul, J. Peters, J. Schmidhuber. Episodic Reinforcement Learning by Logistic Reward-Weighted Regression. In J. Koutnik V. Kurkova, R. Neruda, editors, Proceedings of the International Conference on Artificial Neural Networks ICANN-2008 ICANN 2008, Prague. Springer-Verlag Berlin Heidelberg, 2008. PDF.

123. D. Wierstra, T. Schaul, J. Peters, J. Schmidhuber. Fitness Expectation Maximization. Proceedings of Parallel Problem Solving from Nature PPSN-2008, Dortmund, 2008. PDF.

122. D. Wierstra, T. Schaul, J. Peters, J. Schmidhuber. Natural Evolution Strategies. Proceedings of IEEE Congress on Evolutionary Computation CEC-2008, Hongkong, 2008. PDF.

121. J. Togelius, F. Gomez, J. Schmidhuber. Learning What to Ignore: Memetic Climbing in Topology and Weight Space. IEEE WCCI 2008, Hong Kong, 2008. PDF.

120. 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. PDF.

119. J. Schmidhuber (see #121 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.

118. D. Wierstra, J. Schmidhuber. Policy Gradient Critics. 18th European Conference on Machine Learning ECML, Warszaw, 2007. PDF.

117. 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. PDF.

116. 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. PDF.

115. A. Graves, S. Fernandez, J. Schmidhuber. Multi-Dimensional Recurrent Neural Networks. Intl. Conf. on Artificial Neural Networks ICANN'07, 2007. Preprint: arxiv:0705.2011. PDF.

114. D. Wierstra, A. Foerster, J. Peters, J. Schmidhuber. Solving Deep Memory POMDPs with Recurrent Policy Gradients. Intl. Conf. on Artificial Neural Networks ICANN'07, 2007. PDF.

113. 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). PDF.

112. 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). PDF.

111. 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 PDF.

110. F. Gomez, J. Schmidhuber, and R. Miikkulainen (2006). Efficient Non-Linear Control through Neuroevolution. Proceedings of the European Conference on Machine Learning (ECML-06, Berlin). PDF.

109. H. Mayer, F. Gomez, D. Wierstra, I. Nagy, A. Knoll, and J. Schmidhuber (2006). A System for Robotic Heart Surgery that Learns to Tie Knots Using Recurrent Neural Networks. Proceedings of the International Conference on Intelligent Robotics and Systems (IROS-06, Beijing). PDF. (Best paper nomination finalist.)

108. A. Graves, S. Fernandez, F. Gomez, J. Schmidhuber. Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks. Proceedings of the International Conference on Machine Learning (ICML-06, Pittsburgh), 2006. PDF.

107. B. Bakker, V. Zhumatiy, G. Gruener, J. Schmidhuber. Quasi-Online Reinforcement Learning for Robots. Proceedings of the International Conference on Robotics and Automation (ICRA-06), Orlando, Florida, 2006. PDF.

106. A. Chernov, J. Schmidhuber. Prefix-like Complexities and Computability in the Limit. Proc. of Second Conference on Computability in Europe, CiE 2006, LNCS 3988, pp. 85-93. Based on TR IDSIA-11-05: PDF.

105. V. Zhumatiy, F. Gomez, M. Hutter, and J. Schmidhuber. Metric State Space Reinforcement Learning for a Vision-Capable Mobile Robot. In Proceedings of the International Conference on Intelligent Autonomous Systems, IAS-06, Tokyo, 2006. PDF.

104. J. Schmidhuber, M. Gagliolo, D. Wierstra, F. Gomez. Evolino for Recurrent Support Vector Machines. In Proceedings of the European Symposium on Artificial Neural Networks (ESANN-06, Bruge), 2006. Based on TR IDSIA-19-05: PDF.

103. M. Gagliolo, J. Schmidhuber. Dynamic Algorithm Portfolios. AIMATH06, Ninth International Symposium on Artificial Intelligence and Mathematics, Fort Lauderdale, Florida, 2006. PDF.

102. J. Schmidhuber. Completely Self-Referential Optimal Reinforcement Learners. In W. Duch et al. (Eds.): Proc. Intl. Conf. on Artificial Neural Networks ICANN'05, LNCS 3697, pp. 223-233, Springer-Verlag Berlin Heidelberg, 2005 (plenary talk). PDF. HTML overview.

101. J. Schmidhuber and D. Wierstra and F. J. Gomez. Evolino: Hybrid Neuroevolution / Optimal Linear Search for Sequence Learning. Proceedings of the 19th International Joint Conference on Artificial Intelligence (IJCAI), Edinburgh, p. 853-858, 2005. PDF.

100. D. Wierstra and F. Gomez and J. Schmidhuber. Modeling systems with internal state using Evolino. In Proc. of the 2005 conference on genetic and evolutionary computation (GECCO), Washington, D. C., pp. 1795-1802, ACM Press, New York, NY, USA, 2005. PDF. Best paper award.

99. F. Gomez and J. Schmidhuber. Co-evolving recurrent neurons learn deep memory POMDPs. In Proc. of the 2005 conference on genetic and evolutionary computation (GECCO), Washington, D. C., pp. 1795-1802, ACM Press, New York, NY, USA, 2005. (Nominated for a best paper award). PDF.

98. J. Schmidhuber. A Technical Justification of Consciousness. Proc. of the 9th annual meeting of the Association for the Scientific Study of Consciousness, ASSC9, Caltech, Pasadena, CA, 2005.

97. F. J. Gomez and J. Schmidhuber. Evolving modular fast-weight networks for control. In W. Duch et al. (Eds.): Proc. Intl. Conf. on Artificial Neural Networks ICANN'05, LNCS 3697, pp. 383-389, Springer-Verlag Berlin Heidelberg, 2005. PDF. HTML overview.

96. A. Graves, S. Fernandez, and J. Schmidhuber. Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition. In W. Duch et al. (Eds.): Proc. Intl. Conf. on Artificial Neural Networks ICANN'05, LNCS 3697, pp. 799-804, Springer-Verlag Berlin Heidelberg, 2005. PDF.

95. M. Gagliolo and J. Schmidhuber. A neural network model for adaptive online time allocation. In W. Duch et al. (Eds.): Proc. Intl. Conf. on Artificial Neural Networks ICANN'05, LNCS 3697, pp. 7-12, Springer-Verlag Berlin Heidelberg, 2005. PDF.

94. M. v. d. Giessen and J. Schmidhuber. Fast color-based object recognition independent of position and orientation. In W. Duch et al. (Eds.): Proc. Intl. Conf. on Artificial Neural Networks ICANN'05, LNCS 3696, pp. 469-474, Springer-Verlag Berlin Heidelberg, 2005. PDF.

93. N. Beringer and A. Graves and F. Schiel and J. Schmidhuber. Classifying unprompted speech by retraining LSTM Nets. In W. Duch et al. (Eds.): Proc. Intl. Conf. on Artificial Neural Networks ICANN'05, LNCS 3696, pp. 575-581, Springer-Verlag Berlin Heidelberg, 2005. PDF.

92. A. Graves and J. Schmidhuber. Framewise Phoneme Classification with Bidirectional LSTM Networks. In Proc. International Joint Conference on Neural Networks IJCNN'05, 2005. PDF.

91. J. Schmidhuber. Self-Motivated Development Through Rewards for Predictor Errors / Improvements. In D. Blank and L. Meeden, editors, Developmental Robotics 2005 AAAI Spring Symposium, March 21-23, 2005, Stanford University, CA. PDF.

90. M. Gagliolo, V. Zhumatiy and J. Schmidhuber. Adaptive Online Time Allocation to Search Algorithms. In J. F. Boulicaut et al., eds., Proceedings of the 15th European Conference on Machine Learning ECML, Pisa, Italy, September 20-24, Springer, 2004.

89. Schmidhuber, J., Zhumatiy, V. and Gagliolo, M. Bias-Optimal Incremental Learning of Control Sequences for Virtual Robots. In Groen, F., Amato, N., Bonarini, A., Yoshida, E., and Kröse, B., editors: Proceedings of the 8-th conference on Intelligent Autonomous Systems, IAS-8, Amsterdam, The Netherlands, pp. 658-665, 2004. PDF.

88. A. Graves, N. Beringer, J. Schmidhuber. A Comparison Between Spiking and Differentiable Recurrent Neural Networks on Spoken Digit Recognition. In Proc. 23rd International Conference on modelling, identification, and control (IASTED), 2004. PDF.

87. B. Bakker and J. Schmidhuber. Hierarchical Reinforcement Learning Based on Subgoal Discovery and Subpolicy Specialization (PDF). In F. Groen, N. Amato, A. Bonarini, E. Yoshida, and B. Kröse (Eds.), Proceedings of the 8-th Conference on Intelligent Autonomous Systems, IAS-8, Amsterdam, The Netherlands, p. 438-445, 2004.

86. A. Graves, D. Eck and N. Beringer, J. Schmidhuber. Biologically Plausible Speech Recognition with LSTM Neural Nets. In J. Ijspeert (Ed.), First Intl. Workshop on Biologically Inspired Approaches to Advanced Information Technology, Bio-ADIT 2004, Lausanne, Switzerland, p. 175-184, 2004. PDF .

85. B. Bakker and J. Schmidhuber. Hierarchical Reinforcement Learning with Subpolicies Specializing for Learned Subgoals. In Proceedings of the 2nd IASTED International Conference on Neural Networks and Computational Intelligence, NCI 2004, Grindelwald, Switzerland, 2004. PDF.

84. J. Schmidhuber. Bias-Optimal Incremental Problem Solving. In S. Becker, S. Thrun, K. Obermayer, eds., Advances in Neural Information Processing Systems 15, NIPS'15, MIT Press, Cambridge MA, p. 1571-1578, 2003. PDF . HTML. (Compact version of Optimal Ordered Problem Solver. )

83. B. Bakker, V. Zhumatiy, G. Gruener, and J. Schmidhuber. A Robot that Reinforcement-Learns to Identify and Memorize Important Previous Observations (PDF). In Proceedings of the 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS2003, 2003.

82. Bakker, B., and Schmidhuber, J. (2003). Hierarchical Reinforcement Learning Based on Automatic Discovery of Subgoals and Specialization of Subpolicies. In Proceedings of the 2003 European Workshop on Reinforcement Learning, EWRL 6, Nancy, France.

81. J. Schmidhuber. The Speed Prior: A New Simplicity Measure Yielding Near-Optimal Computable Predictions. In J. Kivinen and R. H. Sloan, editors, Proceedings of the 15th Annual Conference on Computational Learning Theory (COLT 2002), Sydney, Australia, Lecture Notes in Artificial Intelligence, pages 216--228. Springer, 2002. PDF . HTML.

80. B. Bakker, F. Linaker, J. Schmidhuber. Reinforcement Learning in Partially Observable Mobile Robot Domains Using Unsupervised Event Extraction. In Proceedings of the 2002 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2002), Lausanne, 2002. PDF .

79. J. Schmidhuber. Recent Progress in the Fields of Universal Learning Algorithms and Optimal Search. In Proceedings of EUNITE 2002, p. 11-20, Albufeira, Portugal, 2002 (invited talk).

78. J. Schmidhuber. Speed Prior and Optimal Simulation of the Future. In M. Ades and L. M. Deschaine, editors, Proceedings of the Business and Industry Symposium, 2002 Advanced Simulation Technologies Conference, San Diego, California. Simulation Series, vol. 34:4, p. 40-45, 2002 (invited).

77. D. Eck and J. Schmidhuber. Finding temporal structure in music: Blues improvisation with LSTM recurrent networks. In S. Bengio, editor, Proc. NNSP 2002, IEEE, 2002. PDF.

76. D. Eck and J. Schmidhuber. Learning The Long-Term Structure of the Blues. In J. Dorronsoro, ed., Proceedings of Int. Conf. on Artificial Neural Networks ICANN'02, Madrid, pages 284-289, Springer, Berlin, 2002. PDF.

75. F. Gers and J. A. Perez-Ortiz and D. Eck and J. Schmidhuber. Learning Context Sensitive Languages with LSTM Trained with Kalman Filters. In J. Dorronsoro, ed., Proceedings of Int. Conf. on Artificial Neural Networks ICANN'02, Madrid, pages 655--660, Springer, Berlin, 2002. PDF.

74. F. A. Gers, J. A. Pérez-Ortiz, D. Eck, and J. Schmidhuber. DEKF-LSTM. In Verleysen, editor, 10th European Symposium on Artificial Neural Networks. ESANN'2002. Proceedings. Brussels, Belgium, pages 369-376, 2002. PDF.

73. J. A. Perez-Ortiz, J. Schmidhuber, F. Gers and D. Eck. Improving Long-Term Online Prediction with Decoupled Extended Kalman Filters. In J. Dorronsoro, ed., Proceedings of Int. Conf. on Artificial Neural Networks ICANN'02, Madrid, pages 1055--1060, Springer, Berlin, 2002. PDF.

72. I. Kwee, M. Hutter, J. Schmidhuber. Market-Based Reinforcement Learning in Partially Observable Worlds. In G. Dorffner, H. Bischof, K. Hornik, eds., Proceedings of Int. Conf. on Artificial Neural Networks ICANN'01, Vienna, LNCS 2130, pages 865-873, Springer, 2001. PDF.

71. F. Gers, D. Eck, J . Schmidhuber. Applying LSTM to Time Series Predictable Through Time-Window Approaches. In G. Dorffner, H. Bischof, K. Hornik, eds., Proceedings of Int. Conf. on Artificial Neural Networks ICANN'01, Vienna, LNCS 2130, pages 669-676, Springer, 2001. PDF.

70. M. Klapper-Rybicka, N. N. Schraudolph, J. Schmidhuber. Unsupervised Learning in LSTM Recurrent Neural Networks. In G. Dorffner, H. Bischof, K. Hornik, eds., Proceedings of Int. Conf. on Artificial Neural Networks ICANN'01, Vienna, LNCS 2130, pages 684-691, Springer, 2001. PDF.

69. F. A. Gers and J. Schmidhuber. Long Short-Term Memory learns context free and context sensitive languages. In Kurkova et. al., editors, Proceedings of the ICANNGA 2001 Conference, volume 1, pages 134-137, Wien,NY, 2001. Springer. PDF.

68. M. Milano, J. Schmidhuber, P. Koumoutsakos. Active Learning with Adaptive Grids. In G. Dorffner, H. Bischof, K. Hornik, eds., Proceedings of Int. Conf. on Artificial Neural Networks ICANN'01, Vienna, LNCS 2130, pages 436-442, Springer, 2001. PDF.

67. J. Schmidhuber. Evolutionary Computation vs Reinforcement Learning. Proceedings of 3rd Asia-Pacific Conference on Simulated Evolution and Learning (SEAL2000), Nagoya, Japan, October 2000. PDF. (Keynote speech)

66. I. W. Kwee and J. Schmidhuber. Direct policy computation by the Liouville Machine. Proceedings of SOAVE 2000, Ilmenau (Germany), 2000. PDF.

65. F. A. Gers and J. Schmidhuber. Neural processing of complex continual input streams. In Proc. IJCNN'2000, Int. Joint Conf. on Neural Networks, Como, Italy, 2000. PDF.

64. F. A. Gers and J. Schmidhuber. Recurrent nets that time and count. In Proc. IJCNN'2000, Int. Joint Conf. on Neural Networks, Como, Italy, 2000. PDF.

63. M. Milano, X. Giannakopoulos, P. Koumoutsakos, and J. Schmidhuber. Evolving strategies for active flow control. Congress on Evolutionary Computation, USA, July 2000. PDF.

62. F. A. Gers and J. Schmidhuber and F. Cummins. Learning to Forget: Continual Prediction with LSTM. In Proc. Int. Conf. on Artificial Neural Networks (ICANN'99), Edinburgh, Scotland, p. 850-855, IEE, London, 1999.

61. J . Schmidhuber. Artificial Curiosity Based on Discovering Novel Algorithmic Predictability Through Coevolution. In P. Angeline, Z. Michalewicz, M. Schoenauer, X. Yao, Z. Zalzala, eds., Congress on Evolutionary Computation, p. 1612-1618, IEEE Press, Piscataway, NJ, 1999.

60. F. Cummins, F. Gers, J . Schmidhuber. Language identification from prosody without explicit features. Proceedings of EUROSPEECH99, 1999.

59. J. Schmidhuber. Contribution to A. A. Frolov and A. A. Ezhof, eds., Discussion on neurocomputers after ten years, Moscow Institute of Engineering and Physics, January 1999, published in Neural Network World 1-2, 112-113, 1999.

58. J. Schmidhuber and J. Zhao. Direct policy search and uncertain policy evaluation. 1999 AAAI Spring Symposium on Search under Uncertain and Incomplete Information, 119-124, Stanford Univ., 1999. Based on TR IDSIA-50-98, 1998.

57. J. Schmidhuber. Direct policy evaluation in stochastic environments with unknown delays. In Abstract Collection of SNOWBIRD: Machines That Learn. Utah, April 1999.

56. S. Hochreiter and J. Schmidhuber. Nonlinear ICA through low-complexity autoencoders. Proceedings of the 1999 IEEE International Symposium on Circuits ans Systems (ISCAS'99), vol 5, p. 53-56, Orlando, Florida, 1999.

55. S. Hochreiter and J. Schmidhuber. Source separation as a by-product of regularization. In M. S. Kearns, S. A. Solla, D. A. Cohn, eds., Advances in Neural Information Processing Systems 11, NIPS'11, p. 459-465, MIT Press, Cambridge MA, 1999. PDF . HTML.

54. S. Hochreiter and J. Schmidhuber. LOCOCODE performs nonlinear ICA without knowing the number of sources. In J.-F. Cardoso and C. Jutten and P. Loubaton, eds., Proceedings of the First International Workshop on Independent Component Analysis and Signal Separation (ICA'99), 149-154, Aussois, France, 1999.

53. J. Schmidhuber. What's interesting? In Abstract Collection of SNOWBIRD: Machines That Learn. Utah, April 1998 (based on TR IDSIA-35-97, 1997).

52. R. Salustowicz and J. Schmidhuber. Evolving structured programs with hierarchical instructions and skip nodes. In Jude Shavlik, ed., Machine Learning: Proceedings of the 15th International Conference (ICML 1998), p. 488-496, Morgan Kaufmann Publishers, San Francisco, CA, 1998.

51. S. Hochreiter and J. Schmidhuber. LOCOCODE versus PCA and ICA. In L. Niklasson and M. Boden and T. Ziemke, eds., Proceedings of the International Conference on Artificial Neural Networks, Sweden, p. 669-674, Springer, London, 1998.

50. M. Wiering and J. Schmidhuber. CMAC Models Learn to Play Soccer. In L. Niklasson and M. Boden and T. Ziemke, eds., Proceedings of the International Conference on Artificial Neural Networks, Sweden, p. 443-448, Springer, London, 1998.

49. M. Wiering and J. Schmidhuber. Learning exploration policies with models. In Proc. CONALD, 1998.

48. M. Wiering and J. Schmidhuber. Efficient model-based exploration. In R. Pfeiffer, B. Blumberg, J. Meyer, S. W. Wilson, eds., From Animals to Animats 5: Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior, p. 223-228, MIT Press, 1998.

47. J. Zhao and J. Schmidhuber. Solving a complex prisoner's dilemma with self-modifying policies. In R. Pfeiffer, B. Blumberg, J. Meyer, S. W. Wilson, eds., From Animals to Animats 5: Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior, p177-182, MIT Press, 1998.

46. M. Wiering and J. Schmidhuber. Speeding up online Q(lambda)-learning. In Proc. Machine Learning: ECML-98, Lecture Notes in Artificial Intelligence, Springer, 1998.

45. S. Hochreiter and J. Schmidhuber. LSTM can solve hard long time lag problems. In M. C. Mozer, M. I. Jordan, T. Petsche, eds., Advances in Neural Information Processing Systems 9, NIPS'9, pages 473-479, MIT Press, Cambridge MA, 1997. PDF . HTML.

44. R. Salustowicz and M. Wiering and J. Schmidhuber. Evolving soccer strategies. In N. Kasabov, R. Kozma, K. Ko, R. O'Shea, G. Coghill, and T. Gedeon, editors, Progress in Connectionist-based Information Systems: Proceedings of the Fourth International Conference on Neural Information Processing ICONIP'97, volume 1, pages 502-505, 1997.

43. S. Hochreiter and J. Schmidhuber. Low-complexity coding and decoding. In K. M. Wong, I. King, D. Yeung, eds., Theoretical Aspects of Neural Computation: a Multidisciplinary Perspective, pages 297-306, Springer, 1997.

42. J. Schmidhuber and J. Zhao. Multiagent learning with the success-story algorithm. In G. Weiss, ed., Distributed Artificial Intelligence Meets Machine Learning, pages 82-93, Springer, Berlin, 1997.

41. R. Salustowicz and M. Wiering and J. Schmidhuber. On learning soccer strategies. In W. Gerstner, A. Germond, M. Hasler, J.-D. Nicoud, eds., Proceedings of the International Conference on Artificial Neural Networks, Lausanne, Switzerland, Springer, 769-774, 1997.

40. S. Hochreiter and J. Schmidhuber. Unsupervised coding with LOCOCODE. In W. Gerstner, A. Germond, M. Hasler, J.-D. Nicoud, eds., Proceedings of the International Conference on Artificial Neural Networks, Lausanne, Switzerland, Springer, 655-660, 1997.

39. R. Salustowicz and J. Schmidhuber. Probabilistic incremental program evolution: stochastic search through program space. In van Someren, M., Widmer, G., editors, Machine Learning: ECML-97, Lecture Notes in Artificial Intelligence 1224, pages 213-220, Springer, 1997.

38. M. Wiering and J. Schmidhuber. Solving POMDPs using Levin search and EIRA. In L. Saitta, ed., Machine Learning: Proceedings of the 13th International Conference (ICML 1996), pages 534-542, Morgan Kaufmann Publishers, San Francisco, CA, 1996. PDF . HTML.

37. J. Zhao and J. Schmidhuber. Incremental self-improvement for life-time multiagent reinforcement learning. In Pattie Maes, Maja Mataric, Jean-Arcady Meyer, Jordan Pollack, and Stewart W. Wilson, eds., From Animals to Animats 4: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior, pages 516-525, MIT Press, Bradford Books, Cambridge, MA, 1996.

36. J. Schmidhuber. The Neural Heat Exchanger. In S. Amari, L. Xu, L. Chan, I. King, K. Leung, eds., Progress in Neural Information Processing: Proceedings of the Intl. Conference on Neural Information Processing, pages 194-197, Springer, Hongkong, 1996. Earlier presentations in talks at various universities since 1990. PDF . HTML.

35. S. Hochreiter and J. Schmidhuber. Bridging long time lags by weight guessing and ``Long Short-Term Memory''. In F. L. Silva, J. C. Principe, L. B. Almeida, eds., Frontiers in Artificial Intelligence and Applications, Volume 37, pages 65-72, IOS Press, Amsterdam, Netherlands, 1996.

34. J. Schmidhuber. Realistic multiagent reinforcement learning. In G. Weiss, ed., Learning in Distributed Artificial Intelligence Systems. Working Notes of the 1996 ECAI Workshop, 1996.

33. J. Schmidhuber. A general method for multiagent learning in unrestricted environments. In 1996 AAAI Syposium on Adaptation, Co-evolution and Learning in Multiagent Systems, TR SS-96-01, pages 84-87, AAAI Press, Menlo Park, Calif., 1996.

32. S. Hochreiter and J. Schmidhuber. Simplifying neural nets by discovering flat minima. In G. Tesauro, D. S. Touretzky and T. K. Leen, eds., Advances in Neural Information Processing Systems 7, NIPS'7, pages 529-536. MIT Press, Cambridge MA, 1995. PDF . HTML.

31. J. Schmidhuber and S. Heil. Predictive coding with neural nets: Application to text compression. In G. Tesauro, D. S. Touretzky and T. K. Leen, eds., Advances in Neural Information Processing Systems 7, NIPS'7, pages 1047-1054. MIT Press, Cambridge MA, 1995. PDF . HTML.

30. J. Schmidhuber. Discovering solutions with low Kolmogorov complexity and high generalization capability. In A. Prieditis and S. Russell, editors, Machine Learning: Proceedings of the Twelfth International Conference (ICML 1995), pages 488-496. Morgan Kaufmann Publishers, San Francisco, CA, 1995. PDF . HTML.

29. J. Schmidhuber. Beyond ``Genetic Programming'': Incremental Self-Improvement. In J. Rosca, ed., Proc. Workshop on Genetic Programming at ML95, pages 42-49. National Resource Lab for the study of Brain and Behavior, 1995.

28. J. Storck, S. Hochreiter, and J. Schmidhuber. Reinforcement-driven information acquisition in non-deterministic environments. In Proc. ICANN'95, vol. 2, pages 159-164. EC2 & CIE, Paris, 1995. PDF . HTML.

27. J. Schmidhuber. A neural network that embeds its own meta-levels. In Proc. of the International Conference on Neural Networks '93, San Francisco. IEEE, 1993.

26. J. Schmidhuber. ``Neural'' redundancy reduction for text compression. In Neural Network World , 3(6):849-853, 1993.

25. J. Schmidhuber. An introspective network that can learn to run its own weight change algorithm. In Proc. of the Intl. Conf. on Artificial Neural Networks, Brighton, pages 191-195. IEE, 1993.

24. J. Schmidhuber. A self-referential weight matrix. In Proceedings of the International Conference on Artificial Neural Networks, Amsterdam, pages 446-451. Springer, 1993. PDF . HTML.

23. J. Schmidhuber. Reducing the ratio between learning complexity and number of time-varying variables in fully recurrent nets. In Proceedings of the International Conference on Artificial Neural Networks, Amsterdam, pages 460-463. Springer, 1993. PDF. HTML.

22. J. Schmidhuber and D. Prelinger. Unsupervised extraction of predictable abstract features. In Proceedings of the International Conference on Artificial Neural Networks, Amsterdam, pages 601-604. Springer, 1993.

21. J. Schmidhuber and D. Prelinger. A novel unsupervised classification method. In Proc. of the Intl. Conf. on Artificial Neural Networks, Brighton, pages 91-96. IEE, 1993.

20. J. Schmidhuber, M. C. Mozer, and D. Prelinger. Continuous history compression. In H. Hüning, S. Neuhauser, M. Raus, and W. Ritschel, editors, Proc. of Intl. Workshop on Neural Networks, RWTH Aachen, pages 87-95. Augustinus, 1993.

19. J. Schmidhuber and R. Wahnsiedler. Planning simple trajectories using neural subgoal generators. In J. A. Meyer, H. L. Roitblat, and S. W. Wilson, editors, Proc. of the 2nd International Conference on Simulation of Adaptive Behavior, pages 196-202. MIT Press, 1992. PDF . HTML without images. HTML & images in German.

18. J. Schmidhuber. Learning unambiguous reduced sequence descriptions. In J. E. Moody, S. J. Hanson, and R. P. Lippman, editors, Advances in Neural Information Processing Systems 4, NIPS'4, pages 291-298. San Mateo, CA: Morgan Kaufmann, 1992. PDF . HTML.

17. J. Schmidhuber. Reinforcement learning in Markovian and non-Markovian environments. In D. S. Lippman, J. E. Moody, and D. S. Touretzky, editors, Advances in Neural Information Processing Systems 3, NIPS'3, pages 500-506. San Mateo, CA: Morgan Kaufmann, 1991. PDF . HTML.

16. J. Schmidhuber. Learning temporary variable binding with dynamic links. In Proc. International Joint Conference on Neural Networks, Singapore, volume 3, pages 2075-2079. IEEE, 1991.

15. J. Schmidhuber. Curious model-building control systems. In Proc. International Joint Conference on Neural Networks, Singapore, volume 2, pages 1458-1463. IEEE, 1991. PDF . HTML.

14. J. Schmidhuber. Adaptive history compression for learning to divide and conquer. In Proc. International Joint Conference on Neural Networks, Singapore, volume 2, pages 1130-1135. IEEE, 1991.

13. J. Schmidhuber. Learning to generate sub-goals for action sequences. In T. Kohonen, K. Mäkisara, O. Simula, and J. Kangas, editors, Artificial Neural Networks, pages 967-972. Elsevier Science Publishers B.V., North-Holland, 1991. PDF . HTML. HTML & images in German.

12. J. Schmidhuber. Adaptive decomposition of time. In T. Kohonen, K. Mäkisara, O. Simula, and J. Kangas, editors, Artificial Neural Networks, pages 909-914. Elsevier Science Publishers B.V., North-Holland, 1991.

11. J. Schmidhuber and R. Huber. Using sequential adaptive neuro-control for efficient learning of rotation and translation invariance. In T. Kohonen, K. Mäkisara, O. Simula, and J. Kangas, editors, Artificial Neural Networks, pages 315-320. Elsevier Science Publishers B.V., North-Holland, 1991.

10. J. Schmidhuber. A possibility for implementing curiosity and boredom in model-building neural controllers. In J. A. Meyer and S. W. Wilson, editors, Proc. of the International Conference on Simulation of Adaptive Behavior: From Animals to Animats, pages 222-227. MIT Press/Bradford Books, 1991. PDF . HTML.

9. J. Schmidhuber. Learning algorithms for networks with internal and external feedback. In D. S. Touretzky, J. L. Elman, T. J. Sejnowski, and G. E. Hinton, editors, Proc. of the 1990 Connectionist Models Summer School, pages 52-61. San Mateo, CA: Morgan Kaufmann, 1990.

8. J. Schmidhuber. An on-line algorithm for dynamic reinforcement learning and planning in reactive environments. In Proc. IEEE/INNS International Joint Conference on Neural Networks, San Diego, volume 2, pages 253-258, 1990.

7. J. Schmidhuber. Reinforcement learning with interacting continually running fully recurrent networks. In Proc. INNC International Neural Network Conference, Paris, volume 2, pages 817-820, 1990.

6. J. Schmidhuber. Temporal difference-driven learning in recurrent networks. In R. Eckmiller, G. Hartmann, and G. Hauske, editors, Parallel Processing in Neural Systems and Computers, pages 209-212. North-Holland, 1990.

5. J. Schmidhuber. Reinforcement-Lernen und adaptive Steuerung. Nachrichten Neuronale Netze, 2:1-3, 1990.

4. J. Schmidhuber. Recurrent networks adjusted by adaptive critics. In Proc. IEEE/INNS International Joint Conference on Neural Networks, Washington, D. C., volume 1, pages 719-722, 1990.

3. J. Schmidhuber. Networks adjusting networks. In J. Kindermann and A. Linden, editors, Proceedings of `Distributed Adaptive Neural Information Processing', St.Augustin, 24.-25.5. 1989, pages 197-208. Oldenbourg, 1990. Extended version: TR FKI-125-90 (revised), Institut für Informatik, TUM.

2. J. Schmidhuber. The neural bucket brigade. In R. Pfeifer, Z. Schreter, Z. Fogelman, and L. Steels, editors, Connectionism in Perspective, pages 439-446. Amsterdam: Elsevier, North-Holland, 1989.

1. J. Schmidhuber. Accelerated learning in back-propagation nets. In R. Pfeifer, Z. Schreter, Z. Fogelman, and L. Steels, editors, Connectionism in Perspective, pages 429 - 438. Amsterdam: Elsevier, North-Holland, 1989.

ADDITIONAL SELECTED PUBLICATIONS (MOSTLY IN JOURNALS) DERIVED FROM PERSONAL GRANTS

Some department heads insist on coauthorship for all papers and books produced in their department, or at least for those financed by their grants. Schmidhuber disagrees with this practice. Here are selected recent publications of postdocs funded through his personal grants:

25. D. Ryabko, M. Hutter. Predicting Non-Stationary Processes, Applied Mathematics Letters, 2008. (J. Schmidhuber's SNF grant 21-113364.)

24. D. Ryabko, M. Hutter. On the Possibility of Learning in Reactive Environments with Arbitrary Dependence. Theoretical Computer Science, 2008. (J. Schmidhuber's SNF grant 21-113364.)

23. 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.)

22. 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.)

21. M. Mastrolilli and M. Hutter. Hybrid Rounding Techniques for Knapsack Problems. Discrete Applied Mathematics 154(4):640-649, 2006. (J. Schmidhuber's SNF grant 20-61847.)

20. A. Chernov. Finite problems and the logic of the weak law of excluded middle. Mathematical Notes 77(1):263--272, 2005. (J. Schmidhuber's SNF grant 200021-113364.)

19. M. Zaffalon and M. Hutter. Robust Inference of Trees. Annals of Mathematics and Artificial Intelligence 45: 215-239, 2005. (J. Schmidhuber's SNF grant 20-61847.)

18. M. Hutter and M. Zaffalon. Distribution of Mutual Information from Complete and Incomplete Data. Computational Statistics \& Data Analysis 48(3):633-657, 2005. (J. Schmidhuber's SNF grant 20-61847.)

17. M. Hutter. On Generalized Computable Universal Priors and their Convergence. Theoretical Computer Science, 2005. (On J. Schmidhuber's SNF grant 20-61847.)

16. A. Chernov. Complexity of Sets Obtained as Values of Propositional Formulas. Mathematical Notes 75 (1-2): 131-139, 2004. (J. Schmidhuber's SNF grant 200021-113364.)

15. M. Hutter. Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability. Springer, Berlin, 2004. (On J. Schmidhuber's SNF grant 20-61847.) HTML and overview of related work.

14. M. Hutter. Convergence and Loss Bounds for Bayesian Sequence Prediction (pdf). IEEE Transactions on Information Theory, 49:8 (2003) 2061-2067. (On J. Schmidhuber's SNF grant 20-61847.)

13. M. Hutter. Optimality of Universal Bayesian Sequence Prediction for General Loss and Alphabet (pdf).
Journal of Machine Learning Research 4, p 971-1000, 2003. (On J. Schmidhuber's SNF grant 20-61847.)

12. D. Eck. Finding downbeats with a relaxation oscillator. Psychological Research, 66(1):18-25, 2002. (On J. Schmidhuber's SNF grant 2000-61558.)

11. N.N. Schraudolph. Fast Curvature Matrix-Vector Products for Second-Order Gradient Descent. Neural Computation, 14(7), 2002. (On J. Schmidhuber's SNF grant 2100-63630.)

10. M. Hutter. The Fastest and Shortest Algorithm for All Well-Defined Problems. International Journal of Foundations of Computer Science, 13:3 (2002) 431-443, 2002. (On J. Schmidhuber's SNF grant 20-61847.)

9. B. Bakker. Reinforcement Learning with Long Short-Term Memory. Advances in Neural Information Processing Systems 13 (NIPS'13), 2002. (On J. Schmidhuber's CSEM grant 2002.)

8. M. Hutter. Distribution of Mutual Information. Advances in Neural Information Processing Systems 13 (NIPS'13), 2002. (On J. Schmidhuber's SNF grant 20-61847.)

7. M. Hutter. Self-optimizing and Pareto-optimal policies in general environments based on Bayes-mixtures. In J. Kivinen and R. H. Sloan, editors, Proceedings of the 15th Annual Conference on Computational Learning Theory (COLT 2002), Sydney, Australia, Lecture Notes in Artificial Intelligence, p. 364-379. Springer, 2002. (On J. Schmidhuber's SNF grant 20-61847.)

6. D. Eck. A positive-evidence model for rhythmical beat induction. Journal of New Music Research, 30:2, 187--200, 2001. (On J. Schmidhuber's SNF grant 2000-61558.)

5. M. Hutter. New Error Bounds for Solomonoff Prediction. Journal of Computer and System Science, 62:4, 653-667, 2001. (On J. Schmidhuber's SNF grant 20-61847.)

4. M. Hutter. General Loss Bounds for Universal Sequence Prediction. Proc. 18th Intl. Conf. on Machine Learning (ICML-2001), p. 210-217, 2001. (On J. Schmidhuber's SNF grant 20-61847.)

3. N.N. Schraudolph and X. Giannakopoulos. Online Independent Component Analysis With Local Learning Rate Adaptation. Advances in Neural Information Processing Systems 12 (NIPS'12), MIT Press, Cambridge 2000. (On J. Schmidhuber's SNF grant 2100-63630.)

2. F. Cummins. Some lengthening factors in English speech combine additively at most rates. Journal of the Acoustical Society of America, 105(1):476-480, 1999 (On J. Schmidhuber's SNF grant 21-49144.)

1. N.N. Schraudolph. A Fast, Compact Approximation of the Exponential Function. Neural Computation 11(4), 1999. (On J. Schmidhuber's SNF grant 2100-63630.)

REPORTS, MANUSCRIPTS, ETC.

Manuscripts containing material not published elsewhere are marked by $\spadesuit$

40. J. Schmidhuber, M. Gagliolo, D. Wierstra, F. Gomez. Evolino for Recurrent Support Vector Machines. TR IDSIA-19-05, v2, 15 Dec 2005. PDF.

39. J. Schmidhuber. Goedel machines: self-referential universal problem solvers making provably optimal self-improvements. TR IDSIA-19-03, 2003 (revised 2004). HTML Overview, HTML Summary, PDF, arXiv, HTML, bibtex.

38. J. Schmidhuber. Optimal Ordered Problem Solver. TR IDSIA-12-02, 31 July 2002. Gzipped postscript , PDF , public archive.

37. J . Schmidhuber. Algorithmic theories of everything. PDF. Technical Report IDSIA-20-00, Version 2.0 (Dec 20, 2000), quant-ph/0011122 (PDF, 50 pages, 10 theorems, 100 refs). HTML . Compare the physics archive http://arXiv.org/abs/quant-ph/0011122.

36. F. Cummins, F. Gers, J . Schmidhuber. Automatic discrimination among languages based on prosody alone. Technical Report IDSIA-03-99, IDSIA, February 1999.

35. F. A. Gers, J. Schmidhuber, and F. Cummins. Learning to forget: Continual prediction with LSTM. Technical Report IDSIA-01-99, IDSIA, February 1999.

34. J. Schmidhuber and J. Zhao. Direct policy search and uncertain policy evaluation. Technical Report IDSIA-50-98, IDSIA, August 1998.

33. J. Schmidhuber. Facial beauty and fractal geometry. Note IDSIA-28-98, IDSIA, June 1998 (1.29M, ca. 4.96 M gunzipped). HTML (ca. 450K, including 5 color figures).

32. R. Salustowicz and J. Schmidhuber. H-PIPE: Facilitating Hierarchical Program Evolution through Skip Nodes. Technical Report IDSIA-8-98, IDSIA, 1998.

31. R. Salustowicz and J. Schmidhuber. Learning to predict through PIPE and automatic task decomposition. Technical Report IDSIA-11-98, IDSIA, April 1998. $\spadesuit$
30. J. Schmidhuber. Femmes Fractales. Report IDSIA-99-97, IDSIA, December 1997. $\spadesuit$
29. R. Salustowicz, M. Wiering and J. Schmidhuber. Learning team strategies with multiple policy-sharing agents: A soccer case study. Technical Report IDSIA-29-97, IDSIA, Lugano, Switzerland, 1997.

28. M. Eldracher, N. N. Schraudolph, and J. Schmidhuber, Processing Images by Semi-Linear Predictability Minimization. Technical Report IDSIA-77-97, 1997.

27. J. Schmidhuber. What's interesting? Technical Report IDSIA-35-97, IDSIA, July 1997 (23 pages, 10 figures, 157 K, 834 K gunzipped). $\spadesuit$
26. S. Hochreiter and J. Schmidhuber. Feature extraction through LOCOCODE. Technical Report FKI-222-97, Fakultät für Informatik, Technische Universität München, June 1997, revised May 1998 (28 pages, 20 figures, 703 K, 4.9 M gunzipped).

25. M. Wiering and J. Schmidhuber. HQ-Learning: Discovering Markovian subgoals for non-Markovian reinforcement learning. Technical Report IDSIA-95-96, IDSIA, October 1996.

24. S. Hochreiter and J. Schmidhuber. Long Short-Term Memory. Technical Report FKI-207-95, Fakultät für Informatik, Technische Universität München, August 1995.

23. J. Schmidhuber and J. Zhao and M. Wiering. Simple principles of metalearning. Technical Report IDSIA-69-96, IDSIA, June 1996.

22. J. Schmidhuber and S. Hochreiter. Guessing can outperform many long time lag algorithms. Technical Note IDSIA-19-96, IDSIA, May 1996. $\spadesuit$
21. J. Schmidhuber. Environment-independent reinforcement acceleration (invited talk at Hongkong University of Science and Technology). Technical Note IDSIA-59-95, June 1995.

20. J. Schmidhuber and B. Foltin. Semilinear predictability minimization produces orientation sensitive edge detectors. Technical Report FKI-201-94, Fakultät für Informatik, Technische Universität München, December 1994.

19. S. Hochreiter and J. Schmidhuber. Flat minimum search finds simple nets. Technical Report FKI-200-94, Fakultät für Informatik, Technische Universität München, December 1994.

18. J. Schmidhuber. On learning how to learn learning strategies. Technical Report FKI-198-94, Fakultät für Informatik, Technische Universität München, November 1994.

17. J. Schmidhuber, J. Storck, and S. Hochreiter. Reinforcement driven information acquisition in nondeterministic environments. Technical Report, Fakultät für Informatik, Technische Universität München, 1994.

16. J. Schmidhuber. Algorithmisch einfache Kunst. Manuscript, 1994. $\spadesuit$
15. J. Schmidhuber. Low-Complexity Art. Report FKI-197-94, Fakultät für Informatik, Technische Universität München, 1994. $\spadesuit$
14. J. Schmidhuber. Discovering problem solutions with low Kolmogorov complexity and high generalization capability. Technical Report FKI-194-94, Fakultät für Informatik, Technische Universität München, 1994.

13. J. Schmidhuber. Steps towards `self-referential' learning. Technical Report CU-CS-627-92, Dept. of Comp. Sci., University of Colorado at Boulder, November 1992. $\spadesuit$
12. J. Schmidhuber and D. Prelinger. Discovering predictable classifications. Technical Report CU-CS-626-92, Dept. of Comp. Sci., University of Colorado at Boulder, November 1992.

11. J. Schmidhuber. Learning factorial codes by predictability minimization. Technical Report CU-CS-565-91, Dept. of Comp. Sci., University of Colorado at Boulder, December 1991.

10. J. Schmidhuber. An O(n³) learning algorithm for fully recurrent networks. Technical Report FKI-151-91, Institut für Informatik, Technische Universität München, May 1991.

9. J. Schmidhuber. Adaptive confidence and adaptive curiosity. Technical Report FKI-149-91, Institut für Informatik, Technische Universität München, April 1991. PDF.

8. J. Schmidhuber. Neural sequence chunkers. Technical Report FKI-148-91, Institut für Informatik, Technische Universität München, April 1991. $\spadesuit$
7. J. Schmidhuber. Learning to control fast-weight memories: An alternative to recurrent nets. Technical Report FKI-147-91, Institut für Informatik, Technische Universität München, March 1991.

6. J. Schmidhuber. Making the world differentiable: On using fully recurrent self-supervised neural networks for dynamic reinforcement learning and planning in non-stationary environments. Technical Report FKI-126-90, Institut für Informatik, Technische Universität München, February 1990 (revised in November). PDF (hand-drawn figures omitted). $\spadesuit$
5. J. Schmidhuber. Networks adjusting networks. Technical Report FKI-125-90, Institut für Informatik, Technische Universität München. Revised in November 1990. $\spadesuit$
4. J. Schmidhuber. Towards compositional learning with dynamic neural networks. Technical Report FKI-129-90, Institut für Informatik, Technische Universität München, 1990.

3. J. Schmidhuber and R. Huber. Learning to generate focus trajectories for attentive vision. Technical Report FKI-128-90, Institut für Informatik, Technische Universität München, 1990.

2. J. Schmidhuber. A local learning algorithm for dynamic feedforward and recurrent networks. Technical Report FKI-124-90, Institut für Informatik, Technische Universität München, 1989.

1. D. Dickmanns, J. Schmidhuber, and A. Winklhofer. Der genetische Algorithmus: Eine Implementierung in Prolog. Fortgeschrittenenpraktikum, Institut für Informatik, Lehrstuhl Prof. Radig, Technische Universität München, 1987. HTML. $\spadesuit$

Back to

Deutsche Heimseite