2009 |
114 | EE | Daniil Ryabko,
Jürgen Schmidhuber:
Using data compressors to construct order tests for homogeneity and component independence.
Appl. Math. Lett. 22(7): 1029-1032 (2009) |
2008 |
113 | EE | Matteo Gagliolo,
Jürgen Schmidhuber:
Towards Distributed Algorithm Portfolios.
DCAI 2008: 634-643 |
112 | EE | Thomas Rückstieß,
Martin Felder,
Jürgen Schmidhuber:
State-Dependent Exploration for Policy Gradient Methods.
ECML/PKDD (2) 2008: 234-249 |
111 | EE | Frank Sehnke,
Christian Osendorfer,
Thomas Rückstieß,
Alex Graves,
Jan Peters,
Jürgen Schmidhuber:
Policy Gradients with Parameter-Based Exploration for Control.
ICANN (1) 2008: 387-396 |
110 | EE | Daan Wierstra,
Tom Schaul,
Jan Peters,
Jürgen Schmidhuber:
Episodic Reinforcement Learning by Logistic Reward-Weighted Regression.
ICANN (1) 2008: 407-416 |
109 | EE | Julian Togelius,
Faustino J. Gomez,
Jürgen Schmidhuber:
Learning what to ignore: Memetic climbing in topology and weight space.
IEEE Congress on Evolutionary Computation 2008: 3274-3281 |
108 | EE | Daan Wierstra,
Tom Schaul,
Jan Peters,
Jürgen Schmidhuber:
Natural Evolution Strategies.
IEEE Congress on Evolutionary Computation 2008: 3381-3387 |
107 | EE | Jürgen Schmidhuber:
Driven by Compression Progress.
KES (1) 2008: 11 |
106 | EE | Alex Graves,
Jürgen Schmidhuber:
Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks.
NIPS 2008: 545-552 |
105 | EE | Daan Wierstra,
Tom Schaul,
Jan Peters,
Jürgen Schmidhuber:
Fitness Expectation Maximization.
PPSN 2008: 337-346 |
104 | EE | Julian Togelius,
Tom Schaul,
Jürgen Schmidhuber,
Faustino J. Gomez:
Countering Poisonous Inputs with Memetic Neuroevolution.
PPSN 2008: 610-619 |
103 | EE | Santiago Fernández,
Alex Graves,
Jürgen Schmidhuber:
Phoneme recognition in TIMIT with BLSTM-CTC
CoRR abs/0804.3269: (2008) |
102 | EE | Matteo Gagliolo,
Jürgen Schmidhuber:
Algorithm Selection as a Bandit Problem with Unbounded Losses
CoRR abs/0807.1494: (2008) |
101 | EE | Jürgen Schmidhuber:
Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes
CoRR abs/0812.4360: (2008) |
2007 |
100 | EE | Jürgen Schmidhuber:
Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity and Creativity.
ALT 2007: 32-33 |
99 | EE | Jürgen Schmidhuber:
Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity.
Discovery Science 2007: 26-38 |
98 | EE | Daan Wierstra,
Jürgen Schmidhuber:
Policy Gradient Critics.
ECML 2007: 466-477 |
97 | EE | Alexander Förster,
Alex Graves,
Jürgen Schmidhuber:
RNN-based Learning of Compact Maps for Efficient Robot Localization.
ESANN 2007: 537-542 |
96 | EE | Alex Graves,
Santiago Fernández,
Jürgen Schmidhuber:
Multi-dimensional Recurrent Neural Networks.
ICANN (1) 2007: 549-558 |
95 | EE | Daan Wierstra,
Alexander Förster,
Jan Peters,
Jürgen Schmidhuber:
Solving Deep Memory POMDPs with Recurrent Policy Gradients.
ICANN (1) 2007: 697-706 |
94 | EE | Santiago Fernández,
Alex Graves,
Jürgen Schmidhuber:
An Application of Recurrent Neural Networks to Discriminative Keyword Spotting.
ICANN (2) 2007: 220-229 |
93 | EE | Santiago Fernández,
Alex Graves,
Jürgen Schmidhuber:
Sequence Labelling in Structured Domains with Hierarchical Recurrent Neural Networks.
IJCAI 2007: 774-779 |
92 | EE | Matteo Gagliolo,
Jürgen Schmidhuber:
Learning Restart Strategies.
IJCAI 2007: 792-797 |
91 | EE | Alex Graves,
Santiago Fernández,
Marcus Liwicki,
Horst Bunke,
Jürgen Schmidhuber:
Unconstrained On-line Handwriting Recognition with Recurrent Neural Networks.
NIPS 2007 |
90 | EE | Jürgen Schmidhuber:
New Millennium AI and the Convergence of History.
Challenges for Computational Intelligence 2007: 15-35 |
89 | EE | Alex Graves,
Santiago Fernández,
Jürgen Schmidhuber:
Multi-Dimensional Recurrent Neural Networks
CoRR abs/0705.2011: (2007) |
88 | EE | Jürgen Schmidhuber:
2006: Celebrating 75 years of AI - History and Outlook: the Next 25 Years
CoRR abs/0708.4311: (2007) |
87 | EE | Daniil Ryabko,
Jürgen Schmidhuber:
Using Data Compressors to Construct Rank Tests
CoRR abs/0709.0670: (2007) |
86 | EE | Jürgen Schmidhuber:
Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity
CoRR abs/0709.0674: (2007) |
85 | EE | Alexey V. Chernov,
Marcus Hutter,
Jürgen Schmidhuber:
Algorithmic Complexity Bounds on Future Prediction Errors
CoRR abs/cs/0701120: (2007) |
84 | EE | Alexey V. Chernov,
Marcus Hutter,
Jürgen Schmidhuber:
Algorithmic complexity bounds on future prediction errors.
Inf. Comput. 205(2): 242-261 (2007) |
83 | EE | Jürgen Schmidhuber,
Daan Wierstra,
Matteo Gagliolo,
Faustino J. Gomez:
Training Recurrent Networks by Evolino.
Neural Computation 19(3): 757-779 (2007) |
2006 |
82 | EE | Jürgen Schmidhuber:
2006: Celebrating 75 Years of AI - History and Outlook: The Next 25 Years.
50 Years of Artificial Intelligence 2006: 29-41 |
81 | EE | Matteo Gagliolo,
Jürgen Schmidhuber:
Impact of Censored Sampling on the Performance of Restart Strategies.
CP 2006: 167-181 |
80 | EE | Alexey V. Chernov,
Jürgen Schmidhuber:
Prefix-Like Complexities and Computability in the Limit.
CiE 2006: 85-93 |
79 | EE | Faustino J. Gomez,
Jürgen Schmidhuber,
Risto Miikkulainen:
Efficient Non-linear Control Through Neuroevolution.
ECML 2006: 654-662 |
78 | EE | Jürgen Schmidhuber,
Matteo Gagliolo,
Daan Wierstra,
Faustino J. Gomez:
Evolino for recurrent support vector machines.
ESANN 2006: 593-598 |
77 | | Viktor Zhumatiy,
Faustino J. Gomez,
Marcus Hutter,
Jürgen Schmidhuber:
Metric State Space Reinforcement Learning for a Vision-Capable Mobile Robot.
IAS 2006: 272-281 |
76 | EE | Alex Graves,
Santiago Fernández,
Faustino J. Gomez,
Jürgen Schmidhuber:
Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks.
ICML 2006: 369-376 |
75 | | Bram Bakker,
Viktor Zhumatiy,
Gabriel Gruener,
Jürgen Schmidhuber:
Quasi-online Reinforcement Learning for Robots.
ICRA 2006: 2997-3002 |
74 | EE | Hermann Georg Mayer,
Faustino J. Gomez,
Daan Wierstra,
Istvan Nagy,
Alois Knoll,
Jürgen Schmidhuber:
A System for Robotic Heart Surgery that Learns to Tie Knots Using Recurrent Neural Networks.
IROS 2006: 543-548 |
73 | EE | Alexey V. Chernov,
Marcus Hutter,
Jürgen Schmidhuber:
Complexity Monotone in Conditions and Future Prediction Errors.
Kolmogorov Complexity and Applications 2006 |
72 | EE | Matteo Gagliolo,
Jürgen Schmidhuber:
Learning dynamic algorithm portfolios.
Ann. Math. Artif. Intell. 47(3-4): 295-328 (2006) |
71 | EE | Viktor Zhumatiy,
Faustino J. Gomez,
Marcus Hutter,
Jürgen Schmidhuber:
Metric State Space Reinforcement Learning for a Vision-Capable Mobile Robot
CoRR abs/cs/0603023: (2006) |
70 | EE | Jürgen Schmidhuber:
New Millennium AI and the Convergence of History
CoRR abs/cs/0606081: (2006) |
69 | EE | Jürgen Schmidhuber:
Developmental robotics, optimal artificial curiosity, creativity, music, and the fine arts.
Connect. Sci. 18(2): 173-187 (2006) |
2005 |
68 | EE | Jürgen Schmidhuber:
Gödel Machines: Towards a Technical Justification of Consciousness.
Adaptive Agents and Multi-Agent Systems 2005: 1-23 |
67 | EE | Daan Wierstra,
Faustino J. Gomez,
Jürgen Schmidhuber:
Modeling systems with internal state using evolino.
GECCO 2005: 1795-1802 |
66 | EE | Faustino J. Gomez,
Jürgen Schmidhuber:
Co-evolving recurrent neurons learn deep memory POMDPs.
GECCO 2005: 491-498 |
65 | EE | Martijn van de Giessen,
Jürgen Schmidhuber:
Fast Color-Based Object Recognition Independent of Position and Orientation.
ICANN (1) 2005: 469-474 |
64 | EE | Nicole Beringer,
Alex Graves,
Florian Schiel,
Jürgen Schmidhuber:
Classifying Unprompted Speech by Retraining LSTM Nets.
ICANN (1) 2005: 575-581 |
63 | EE | Jürgen Schmidhuber:
Completely Self-referential Optimal Reinforcement Learners.
ICANN (2) 2005: 223-233 |
62 | EE | Faustino J. Gomez,
Jürgen Schmidhuber:
Evolving Modular Fast-Weight Networks for Control.
ICANN (2) 2005: 383-389 |
61 | EE | Matteo Gagliolo,
Jürgen Schmidhuber:
A Neural Network Model for Inter-problem Adaptive Online Time Allocation.
ICANN (2) 2005: 7-12 |
60 | EE | Alex Graves,
Santiago Fernández,
Jürgen Schmidhuber:
Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition.
ICANN (2) 2005: 799-804 |
59 | EE | Jürgen Schmidhuber,
Daan Wierstra,
Faustino J. Gomez:
Evolino: Hybrid Neuroevolution/Optimal Linear Search for Sequence Learning.
IJCAI 2005: 853-858 |
58 | EE | Jürgen Schmidhuber,
Matteo Gagliolo,
Daan Wierstra,
Faustino J. Gomez:
Evolino for recurrent support vector machines
CoRR abs/cs/0512062: (2005) |
57 | EE | Alex Graves,
Jürgen Schmidhuber:
Framewise phoneme classification with bidirectional LSTM and other neural network architectures.
Neural Networks 18(5-6): 602-610 (2005) |
2004 |
56 | EE | Alex Graves,
Douglas Eck,
Nicole Beringer,
Jürgen Schmidhuber:
Biologically Plausible Speech Recognition with LSTM Neural Nets.
BioADIT 2004: 127-136 |
55 | EE | Matteo Gagliolo,
Viktor Zhumatiy,
Jürgen Schmidhuber:
Adaptive Online Time Allocation to Search Algorithms.
ECML 2004: 134-143 |
54 | | Bram Bakker,
Jürgen Schmidhuber:
Hierarchical reinforcement learning with subpolicies specializing for learned subgoals.
Neural Networks and Computational Intelligence 2004: 125-130 |
53 | | Alex Graves,
Nicole Beringer,
Jürgen Schmidhuber:
A comparison between spiking and differentiable recurrent neural networks on spoken digit recognition.
Neural Networks and Computational Intelligence 2004: 164-168 |
52 | EE | Jürgen Schmidhuber:
Optimal Ordered Problem Solver.
Machine Learning 54(3): 211-254 (2004) |
2003 |
51 | EE | Jürgen Schmidhuber:
The New AI: General & Sound & Relevant for Physics
CoRR cs.AI/0302012: (2003) |
50 | EE | Jürgen Schmidhuber:
Goedel Machines: Self-Referential Universal Problem Solvers Making Provably Optimal Self-Improvements
CoRR cs.LO/0309048: (2003) |
49 | EE | Juan Antonio Pérez-Ortiz,
Felix A. Gers,
Douglas Eck,
Jürgen Schmidhuber:
Kalman filters improve LSTM network performance in problems unsolvable by traditional recurrent nets.
Neural Networks 16(2): 241-250 (2003) |
2002 |
48 | EE | Jürgen Schmidhuber:
The Speed Prior: A New Simplicity Measure Yielding Near-Optimal Computable Predictions.
COLT 2002: 216-228 |
47 | | Felix A. Gers,
Juan Antonio Pérez-Ortiz,
Douglas Eck,
Jürgen Schmidhuber:
DEKF-LSTM.
ESANN 2002: 369-376 |
46 | EE | Juan Antonio Pérez-Ortiz,
Jürgen Schmidhuber,
Felix A. Gers,
Douglas Eck:
Improving Long-Term Online Prediction with Decoupled Extended Kalman Filters.
ICANN 2002: 1055-1069 |
45 | EE | Douglas Eck,
Jürgen Schmidhuber:
Learning the Long-Term Structure of the Blues.
ICANN 2002: 284-289 |
44 | EE | Felix A. Gers,
Juan Antonio Pérez-Ortiz,
Douglas Eck,
Jürgen Schmidhuber:
Learning Context Sensitive Languages with LSTM Trained with Kalman Filters.
ICANN 2002: 655-660 |
43 | EE | Jürgen Schmidhuber:
Bias-Optimal Incremental Problem Solving.
NIPS 2002: 1547-1546 |
42 | EE | Jürgen Schmidhuber:
Optimal Ordered Problem Solver
CoRR cs.AI/0207097: (2002) |
41 | EE | Jürgen Schmidhuber:
Hierarchies of Generalized Kolmogorov Complexities and Nonenumerable Universal Measures Computable in the Limit.
Int. J. Found. Comput. Sci. 13(4): 587-612 (2002) |
40 | EE | Felix A. Gers,
Nicol N. Schraudolph,
Jürgen Schmidhuber:
Learning Precise Timing with LSTM Recurrent Networks.
Journal of Machine Learning Research 3: 115-143 (2002) |
39 | EE | Jürgen Schmidhuber,
Felix A. Gers,
Douglas Eck:
Learning Nonregular Languages: A Comparison of Simple Recurrent Networks and LSTM.
Neural Computation 14(9): 2039-2041 (2002) |
2001 |
38 | EE | Michele Milano,
Jürgen Schmidhuber,
Petros Koumoutsakos:
Active Learning with Adaptive Grids.
ICANN 2001: 436-442 |
37 | EE | Felix A. Gers,
Douglas Eck,
Jürgen Schmidhuber:
Applying LSTM to Time Series Predictable through Time-Window Approaches.
ICANN 2001: 669-676 |
36 | EE | Magdalena Klapper-Rybicka,
Nicol N. Schraudolph,
Jürgen Schmidhuber:
Unsupervised Learning in LSTM Recurrent Neural Networks.
ICANN 2001: 684-691 |
35 | EE | Ivo Kwee,
Marcus Hutter,
Jürgen Schmidhuber:
Market-Based Reinforcement Learning in Partially Observable Worlds.
ICANN 2001: 865-873 |
34 | EE | Jürgen Schmidhuber:
Sequential Decision Making Based on Direct Search.
Sequence Learning 2001: 213-240 |
33 | EE | Ivo Kwee,
Marcus Hutter,
Jürgen Schmidhuber:
Market-Based Reinforcement Learning in Partially Observable Worlds
CoRR cs.AI/0105025: (2001) |
32 | EE | Ivo Kwee,
Marcus Hutter,
Jürgen Schmidhuber:
Gradient-based Reinforcement Planning in Policy-Search Methods
CoRR cs.AI/0111060: (2001) |
2000 |
31 | EE | Felix A. Gers,
Jürgen Schmidhuber:
Recurrent Nets that Time and Count.
IJCNN (3) 2000: 189-194 |
30 | EE | Felix A. Gers,
Jürgen Schmidhuber:
Neural Processing of Complex Continual Input Streams.
IJCNN (4) 2000: 557-562 |
29 | EE | Jürgen Schmidhuber:
Algorithmic Theories of Everything
CoRR quant-ph/0011122: (2000) |
28 | | Felix A. Gers,
Jürgen Schmidhuber,
Fred A. Cummins:
Learning to Forget: Continual Prediction with LSTM.
Neural Computation 12(10): 2451-2471 (2000) |
1999 |
27 | EE | Sepp Hochreiter,
Jürgen Schmidhuber:
Nonlinear ICA through low-complexity autoencoders.
ISCAS (5) 1999: 53-56 |
26 | | Marco Wiering,
Rafal Salustowicz,
Jürgen Schmidhuber:
Reinforcement Learning Soccer Teams with Incomplete World Models.
Auton. Robots 7(1): 77-88 (1999) |
25 | EE | Jürgen Schmidhuber:
A Computer Scientist's View of Life, the Universe, and Everything
CoRR quant-ph/9904050: (1999) |
24 | | Sepp Hochreiter,
Jürgen Schmidhuber:
Feature Extraction Through LOCOCODE.
Neural Computation 11(3): 679-714 (1999) |
1998 |
23 | | Marco Wiering,
Jürgen Schmidhuber:
Speeding up Q(lambda)-Learning.
ECML 1998: 352-363 |
22 | | Rafal Salustowicz,
Jürgen Schmidhuber:
Evolving Structured Programs with Hierarchical Instructions and Skip Nodes.
ICML 1998: 488-496 |
21 | EE | Sepp Hochreiter,
Jürgen Schmidhuber:
Source Separation as a By-Product of Regularization.
NIPS 1998: 459-465 |
20 | | Marco Wiering,
Jürgen Schmidhuber:
Fast Online Q(lambda).
Machine Learning 33(1): 105-115 (1998) |
19 | | Rafal Salustowicz,
Marco Wiering,
Jürgen Schmidhuber:
Learning Team Strategies: Soccer Case Studies.
Machine Learning 33(2-3): 263-282 (1998) |
1997 |
18 | | Rafal Salustowicz,
Jürgen Schmidhuber:
Probabilistic Incremental Program Evolution: Stochastic Search Through Program Space.
ECML 1997: 213-220 |
17 | EE | Jürgen Schmidhuber:
A Computer Scientist's View of Life, the Universe, and Everything.
Foundations of Computer Science: Potential - Theory - Cognition 1997: 201-208 |
16 | | Sepp Hochreiter,
Jürgen Schmidhuber:
Unsupervised Coding with LOCOCODE.
ICANN 1997: 655-660 |
15 | | Rafal Salustowicz,
Marco Wiering,
Jürgen Schmidhuber:
On Learning Soccer Strategies.
ICANN 1997: 769-774 |
14 | | Rafal Salustowicz,
Jürgen Schmidhuber:
Probabilistic Incremental Program Evolution.
Evolutionary Computation 5(2): 123-141 (1997) |
13 | | Jürgen Schmidhuber,
Jieyu Zhao,
Marco Wiering:
Shifting Inductive Bias with Success-Story Algorithm, Adaptive Levin Search, and Incremental Self-Improvement.
Machine Learning 28(1): 105-130 (1997) |
12 | EE | Sepp Hochreiter,
Jürgen Schmidhuber:
Flat Minima
Neural Computation 9(1): 1-42 (1997) |
11 | EE | Sepp Hochreiter,
Jürgen Schmidhuber:
Long Short-Term Memory.
Neural Computation 9(8): 1735-1780 (1997) |
10 | EE | Jürgen Schmidhuber:
Discovering Neural Nets with Low Kolmogorov Complexity and High Generalization Capability.
Neural Networks 10(5): 857-873 (1997) |
1996 |
9 | | Jürgen Schmidhuber,
Jieyu Zhao:
Multi-Agent Learning with the Success-Story Algorithm.
ECAI Workshop LDAIS / ICMAS Workshop LIOME 1996: 82-93 |
8 | | Marco Wiering,
Jürgen Schmidhuber:
Solving POMDPs with Levin Search and EIRA.
ICML 1996: 534-542 |
7 | EE | Sepp Hochreiter,
Jürgen Schmidhuber:
LSTM can Solve Hard Long Time Lag Problems.
NIPS 1996: 473-479 |
1995 |
6 | | Jürgen Schmidhuber:
Discovering Solutions with Low Kolmogorov Complexity and High Generalization Capability.
ICML 1995: 488-496 |
1994 |
5 | EE | Jürgen Schmidhuber,
Stefan Heil:
Predictive Coding with Neural Nets: Application to Text Compression.
NIPS 1994: 1047-1054 |
4 | EE | Sepp Hochreiter,
Jürgen Schmidhuber:
Simplifying Neural Nets by Discovering Flat Minima.
NIPS 1994: 529-536 |
1991 |
3 | EE | Jürgen Schmidhuber:
Learning Unambiguous Reduced Sequence Descriptions.
NIPS 1991: 291-298 |
2 | EE | Jürgen Schmidhuber,
Rudolf Huber:
Learning to Generate Artificial Fovea Trajectories for Target Detection.
Int. J. Neural Syst. 2(1-2): 125-134 (1991) |
1990 |
1 | EE | Jürgen Schmidhuber:
Reinforcement Learning in Markovian and Non-Markovian Environments.
NIPS 1990: 500-506 |