Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDJürgen Schmidhuber
Person information
- affiliation: King Abdullah University of Science and Technology (KAUST), Saudi Arabia
- affiliation (former): University of Applied Sciences and Arts of Southern Switzerland, Switzerland
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2023
[j76]Anand Gopalakrishnan, Kazuki Irie, Jürgen Schmidhuber, Sjoerd van Steenkiste:
Unsupervised Learning of Temporal Abstractions With Slot-Based Transformers. Neural Comput. 35(4): 593-626 (2023)- [c235]Francesco Faccio, Vincent Herrmann, Aditya Ramesh, Louis Kirsch, Jürgen Schmidhuber:
Goal-Conditioned Generators of Deep Policies. AAAI 2023: 7503-7511 - [c234]Kazuki Irie, Jürgen Schmidhuber:
Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules. ICLR 2023 - [c233]Kenny John Young, Aditya Ramesh, Louis Kirsch, Jürgen Schmidhuber:
The Benefits of Model-Based Generalization in Reinforcement Learning. ICML 2023: 40254-40276 - [i134]Deyao Zhu
, Yuhui Wang, Jürgen Schmidhuber, Mohamed Elhoseiny:
Guiding Online Reinforcement Learning with Action-Free Offline Pretraining. CoRR abs/2301.12876 (2023) - [i133]Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber:
Topological Neural Discrete Representation Learning à la Kohonen. CoRR abs/2302.07950 (2023) - [i132]Kazuki Irie, Jürgen Schmidhuber:
Accelerating Neural Self-Improvement via Bootstrapping. CoRR abs/2305.01547 (2023) - [i131]Imanol Schlag, Sainbayar Sukhbaatar, Asli Celikyilmaz, Wen-tau Yih, Jason Weston, Jürgen Schmidhuber, Xian Li:
Large Language Model Programs. CoRR abs/2305.05364 (2023) - [i130]Aleksandar Stanic, Anand Gopalakrishnan, Kazuki Irie, Jürgen Schmidhuber:
Contrastive Training of Complex-Valued Autoencoders for Object Discovery. CoRR abs/2305.15001 (2023) - [i129]Mingchen Zhuge, Haozhe Liu, Francesco Faccio, Dylan R. Ashley, Róbert Csordás, Anand Gopalakrishnan, Abdullah Hamdi, Hasan Abed Al Kader Hammoud, Vincent Herrmann, Kazuki Irie, Louis Kirsch, Bing Li, Guohao Li, Shuming Liu, Jinjie Mai, Piotr Piekos, Aditya Ramesh, Imanol Schlag, Weimin Shi, Aleksandar Stanic, Wenyi Wang, Yuhui Wang, Mengmeng Xu, Deng-Ping Fan, Bernard Ghanem, Jürgen Schmidhuber:
Mindstorms in Natural Language-Based Societies of Mind. CoRR abs/2305.17066 (2023) - [i128]Kazuki Irie, Anand Gopalakrishnan, Jürgen Schmidhuber:
Exploring the Promise and Limits of Real-Time Recurrent Learning. CoRR abs/2305.19044 (2023) - [i127]Haozhe Liu, Mingchen Zhuge, Bing Li, Yuhui Wang, Francesco Faccio, Bernard Ghanem, Jürgen Schmidhuber:
Learning to Identify Critical States for Reinforcement Learning from Videos. CoRR abs/2308.07795 (2023) - [i126]Aleksandar Stanic, Dylan R. Ashley, Oleg Serikov, Louis Kirsch, Francesco Faccio, Jürgen Schmidhuber, Thomas Hofmann, Imanol Schlag:
The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute. CoRR abs/2309.11197 (2023) - 2022
- [j75]Lukas Tuggener, Jürgen Schmidhuber, Thilo Stadelmann:
Is it enough to optimize CNN architectures on ImageNet? Frontiers Comput. Sci. 4 (2022) - [j74]Noor Sajid, Francesco Faccio, Lancelot Da Costa, Thomas Parr, Jürgen Schmidhuber, Karl J. Friston:
Bayesian Brains and the Rényi Divergence. Neural Comput. 34(4): 829-855 (2022) - [j73]Aditya Ramesh, Paulo E. Rauber, Michelangelo Conserva, Jürgen Schmidhuber:
Recurrent Neural-Linear Posterior Sampling for Nonstationary Contextual Bandits. Neural Comput. 34(11): 2232-2272 (2022) - [j72]Michael Wand, Morten Bak Kristoffersen, Andreas W. Franzke, Jürgen Schmidhuber:
Analysis of Neural Network Based Proportional Myoelectric Hand Prosthesis Control. IEEE Trans. Biomed. Eng. 69(7): 2283-2293 (2022) - [c232]Miroslav Strupl, Francesco Faccio, Dylan R. Ashley, Rupesh Kumar Srivastava, Jürgen Schmidhuber:
Reward-Weighted Regression Converges to a Global Optimum. AAAI 2022: 8361-8369 - [c231]Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber:
CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations. EMNLP 2022: 9758-9767 - [c230]Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber:
The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization. ICLR 2022 - [c229]Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber:
The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention. ICML 2022: 9639-9659 - [c228]Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber:
A Modern Self-Referential Weight Matrix That Learns to Modify Itself. ICML 2022: 9660-9677 - [c227]Kazuki Irie, Francesco Faccio, Jürgen Schmidhuber:
Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules. NeurIPS 2022 - [c226]Aditya Ramesh, Louis Kirsch, Sjoerd van Steenkiste, Jürgen Schmidhuber:
Exploring through Random Curiosity with General Value Functions. NeurIPS 2022 - [i125]Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber:
A Modern Self-Referential Weight Matrix That Learns to Modify Itself. CoRR abs/2202.05780 (2022) - [i124]Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber:
The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention. CoRR abs/2202.05798 (2022) - [i123]Kai Arulkumaran, Dylan R. Ashley, Jürgen Schmidhuber, Rupesh Kumar Srivastava:
All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL. CoRR abs/2202.11960 (2022) - [i122]Dylan R. Ashley, Kai Arulkumaran, Jürgen Schmidhuber, Rupesh Kumar Srivastava:
Learning Relative Return Policies With Upside-Down Reinforcement Learning. CoRR abs/2202.12742 (2022) - [i121]Anand Gopalakrishnan, Kazuki Irie, Jürgen Schmidhuber, Sjoerd van Steenkiste:
Unsupervised Learning of Temporal Abstractions with Slot-based Transformers. CoRR abs/2203.13573 (2022) - [i120]Miroslav Strupl, Francesco Faccio, Dylan R. Ashley, Jürgen Schmidhuber, Rupesh Kumar Srivastava:
Upside-Down Reinforcement Learning Can Diverge in Stochastic Environments With Episodic Resets. CoRR abs/2205.06595 (2022) - [i119]Kazuki Irie, Francesco Faccio, Jürgen Schmidhuber:
Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules. CoRR abs/2206.01649 (2022) - [i118]Francesco Faccio, Aditya Ramesh, Vincent Herrmann, Jean Harb, Jürgen Schmidhuber:
General Policy Evaluation and Improvement by Learning to Identify Few But Crucial States. CoRR abs/2207.01566 (2022) - [i117]Francesco Faccio, Vincent Herrmann, Aditya Ramesh, Louis Kirsch, Jürgen Schmidhuber:
Goal-Conditioned Generators of Deep Policies. CoRR abs/2207.01570 (2022) - [i116]Aleksandar Stanic, Yujin Tang, David Ha, Jürgen Schmidhuber:
Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter. CoRR abs/2208.03374 (2022) - [i115]Kazuki Irie, Jürgen Schmidhuber:
Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules. CoRR abs/2210.06184 (2022) - [i114]Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber:
CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations. CoRR abs/2210.06350 (2022) - [i113]Kenny Young, Aditya Ramesh, Louis Kirsch, Jürgen Schmidhuber:
The Benefits of Model-Based Generalization in Reinforcement Learning. CoRR abs/2211.02222 (2022) - [i112]Kazuki Irie, Jürgen Schmidhuber:
Learning to Control Rapidly Changing Synaptic Connections: An Alternative Type of Memory in Sequence Processing Artificial Neural Networks. CoRR abs/2211.09440 (2022) - [i111]Aditya Ramesh, Louis Kirsch, Sjoerd van Steenkiste, Jürgen Schmidhuber:
Exploring through Random Curiosity with General Value Functions. CoRR abs/2211.10282 (2022) - [i110]Dylan R. Ashley, Vincent Herrmann, Zachary Friggstad, Jürgen Schmidhuber:
On Narrative Information and the Distillation of Stories. CoRR abs/2211.12423 (2022) - [i109]Jürgen Schmidhuber:
Annotated History of Modern AI and Deep Learning. CoRR abs/2212.11279 (2022) - [i108]Vincent Herrmann, Louis Kirsch, Jürgen Schmidhuber:
Learning One Abstract Bit at a Time Through Self-Invented Experiments Encoded as Neural Networks. CoRR abs/2212.14374 (2022) - [i107]Louis Kirsch, Jürgen Schmidhuber:
Eliminating Meta Optimization Through Self-Referential Meta Learning. CoRR abs/2212.14392 (2022) - 2021
- [j71]Paulo E. Rauber, Avinash Ummadisingu, Filipe Mutz, Jürgen Schmidhuber:
Reinforcement Learning in Sparse-Reward Environments With Hindsight Policy Gradients. Neural Comput. 33(6): 1498-1553 (2021) - [j70]Ariel Ruiz-Garcia, Jürgen Schmidhuber, Vasile Palade, Clive Cheong Took, Danilo P. Mandic:
Deep neural network representation and Generative Adversarial Learning. Neural Networks 139: 199-200 (2021) - [c225]Aleksandar Stanic, Sjoerd van Steenkiste, Jürgen Schmidhuber:
Hierarchical Relational Inference. AAAI 2021: 9730-9738 - [c224]Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber:
The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers. EMNLP (1) 2021: 619-634 - [c223]Róbert Csordás, Sjoerd van Steenkiste, Jürgen Schmidhuber:
Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks. ICLR 2021 - [c222]Francesco Faccio, Louis Kirsch, Jürgen Schmidhuber:
Parameter-Based Value Functions. ICLR 2021 - [c221]Anand Gopalakrishnan, Sjoerd van Steenkiste, Jürgen Schmidhuber:
Unsupervised Object Keypoint Learning using Local Spatial Predictability. ICLR 2021 - [c220]Ðorðe Miladinovic, Aleksandar Stanic, Stefan Bauer, Jürgen Schmidhuber, Joachim M. Buhmann:
Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling. ICLR 2021 - [c219]Imanol Schlag, Tsendsuren Munkhdalai, Jürgen Schmidhuber:
Learning Associative Inference Using Fast Weight Memory. ICLR 2021 - [c218]Imanol Schlag, Kazuki Irie, Jürgen Schmidhuber:
Linear Transformers Are Secretly Fast Weight Programmers. ICML 2021: 9355-9366 - [c217]Krsto Prorokovic, Michael Wand, Jürgen Schmidhuber:
Improving Stateful Premise Selection with Transformers. CICM 2021: 84-89 - [c216]Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber:
Going Beyond Linear Transformers with Recurrent Fast Weight Programmers. NeurIPS 2021: 7703-7717 - [c215]Louis Kirsch, Jürgen Schmidhuber:
Meta Learning Backpropagation And Improving It. NeurIPS 2021: 14122-14134 - [i106]Imanol Schlag, Kazuki Irie, Jürgen Schmidhuber:
Linear Transformers Are Secretly Fast Weight Memory Systems. CoRR abs/2102.11174 (2021) - [i105]Djordje Miladinovic, Aleksandar Stanic, Stefan Bauer, Jürgen Schmidhuber, Joachim M. Buhmann:
Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling. CoRR abs/2103.08877 (2021) - [i104]Lukas Tuggener, Jürgen Schmidhuber, Thilo Stadelmann:
Is it Enough to Optimize CNN Architectures on ImageNet? CoRR abs/2103.09108 (2021) - [i103]Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber:
Going Beyond Linear Transformers with Recurrent Fast Weight Programmers. CoRR abs/2106.06295 (2021) - [i102]Noor Sajid, Francesco Faccio, Lancelot Da Costa, Thomas Parr, Jürgen Schmidhuber, Karl J. Friston:
Bayesian brains and the Rényi divergence. CoRR abs/2107.05438 (2021) - [i101]Miroslav Strupl, Francesco Faccio, Dylan R. Ashley, Rupesh Kumar Srivastava, Jürgen Schmidhuber:
Reward-Weighted Regression Converges to a Global Optimum. CoRR abs/2107.09088 (2021) - [i100]Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber:
The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers. CoRR abs/2108.12284 (2021) - [i99]Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber:
The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization. CoRR abs/2110.07732 (2021) - [i98]Dylan R. Ashley, Vincent Herrmann, Zachary Friggstad, Kory W. Mathewson, Jürgen Schmidhuber:
Automatic Embedding of Stories Into Collections of Independent Media. CoRR abs/2111.02216 (2021) - [i97]Kazuki Irie, Jürgen Schmidhuber:
Training and Generating Neural Networks in Compressed Weight Space. CoRR abs/2112.15545 (2021) - [i96]Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber:
Improving Baselines in the Wild. CoRR abs/2112.15550 (2021) - 2020
- [j69]Jürgen Schmidhuber:
Generative Adversarial Networks are special cases of Artificial Curiosity (1990) and also closely related to Predictability Minimization (1991). Neural Networks 127: 58-66 (2020) - [j68]Sjoerd van Steenkiste, Karol Kurach, Jürgen Schmidhuber, Sylvain Gelly:
Investigating object compositionality in Generative Adversarial Networks. Neural Networks 130: 309-325 (2020) - [c214]Matteo Riva, Michael Wand, Jürgen Schmidhuber:
Motion Dynamics Improve Speaker-Independent Lipreading. ICASSP 2020: 4407-4411 - [c213]Louis Kirsch, Sjoerd van Steenkiste, Jürgen Schmidhuber:
Improving Generalization in Meta Reinforcement Learning using Learned Objectives. ICLR 2020 - [c212]Lukas Tuggener, Yvan Putra Satyawan, Alexander Pacha, Jürgen Schmidhuber, Thilo Stadelmann:
The DeepScoresV2 Dataset and Benchmark for Music Object Detection. ICPR 2020: 9188-9195 - [c211]Michael Wand, Jürgen Schmidhuber:
Fusion Architectures for Word-Based Audiovisual Speech Recognition. INTERSPEECH 2020: 3491-3495 - [i95]Jürgen Schmidhuber:
Deep Learning: Our Miraculous Year 1990-1991. CoRR abs/2005.05744 (2020) - [i94]Francesco Faccio, Jürgen Schmidhuber:
Parameter-based Value Functions. CoRR abs/2006.09226 (2020) - [i93]Aditya Ramesh, Paulo E. Rauber, Jürgen Schmidhuber:
Recurrent Neural-Linear Posterior Sampling for Non-Stationary Contextual Bandits. CoRR abs/2007.04750 (2020) - [i92]Róbert Csordás, Sjoerd van Steenkiste, Jürgen Schmidhuber:
Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks. CoRR abs/2010.02066 (2020) - [i91]Aleksandar Stanic, Sjoerd van Steenkiste, Jürgen Schmidhuber:
Hierarchical Relational Inference. CoRR abs/2010.03635 (2020) - [i90]Imanol Schlag, Tsendsuren Munkhdalai, Jürgen Schmidhuber:
Learning Associative Inference Using Fast Weight Memory. CoRR abs/2011.07831 (2020) - [i89]Anand Gopalakrishnan, Sjoerd van Steenkiste, Jürgen Schmidhuber:
Unsupervised Object Keypoint Learning using Local Spatial Predictability. CoRR abs/2011.12930 (2020) - [i88]Klaus Greff, Sjoerd van Steenkiste, Jürgen Schmidhuber:
On the Binding Problem in Artificial Neural Networks. CoRR abs/2012.05208 (2020) - [i87]Louis Kirsch, Jürgen Schmidhuber:
Meta Learning Backpropagation And Improving It. CoRR abs/2012.14905 (2020)
2010 – 2019
- 2019
- [c210]Krsto Prorokovic, Michael Wand, Tanja Schultz, Jürgen Schmidhuber:
Adaptation of an EMG-Based Speech Recognizer via Meta-Learning. GlobalSIP 2019: 1-5 - [c209]Róbert Csordás, Jürgen Schmidhuber:
Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control. ICLR (Poster) 2019 - [c208]Paulo E. Rauber, Avinash Ummadisingu, Filipe Mutz, Jürgen Schmidhuber:
Hindsight policy gradients. ICLR (Poster) 2019 - [c207]Sjoerd van Steenkiste, Francesco Locatello, Jürgen Schmidhuber, Olivier Bachem:
Are Disentangled Representations Helpful for Abstract Visual Reasoning? NeurIPS 2019: 14222-14235 - [i86]Róbert Csordás, Jürgen Schmidhuber:
Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control. CoRR abs/1904.10278 (2019) - [i85]Sjoerd van Steenkiste, Francesco Locatello, Jürgen Schmidhuber, Olivier Bachem:
Are Disentangled Representations Helpful for Abstract Visual Reasoning? CoRR abs/1905.12506 (2019) - [i84]Sjoerd van Steenkiste, Klaus Greff, Jürgen Schmidhuber:
A Perspective on Objects and Systematic Generalization in Model-Based RL. CoRR abs/1906.01035 (2019) - [i83]Jürgen Schmidhuber:
Unsupervised Minimax: Adversarial Curiosity, Generative Adversarial Networks, and Predictability Minimization. CoRR abs/1906.04493 (2019) - [i82]Timon Willi, Jonathan Masci, Jürgen Schmidhuber, Christian Osendorfer:
Recurrent Neural Processes. CoRR abs/1906.05915 (2019) - [i81]Louis Kirsch, Sjoerd van Steenkiste, Jürgen Schmidhuber:
Improving Generalization in Meta Reinforcement Learning using Learned Objectives. CoRR abs/1910.04098 (2019) - [i80]Aleksandar Stanic, Jürgen Schmidhuber:
R-SQAIR: Relational Sequential Attend, Infer, Repeat. CoRR abs/1910.05231 (2019) - [i79]Imanol Schlag, Paul Smolensky, Roland Fernandez, Nebojsa Jojic, Jürgen Schmidhuber, Jianfeng Gao:
Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving. CoRR abs/1910.06611 (2019) - [i78]Jürgen Schmidhuber:
Reinforcement Learning Upside Down: Don't Predict Rewards - Just Map Them to Actions. CoRR abs/1912.02875 (2019) - [i77]Rupesh Kumar Srivastava, Pranav Shyam, Filipe Mutz, Wojciech Jaskowski, Jürgen Schmidhuber:
Training Agents using Upside-Down Reinforcement Learning. CoRR abs/1912.02877 (2019) - 2018
- [c206]Michael Wand, Jürgen Schmidhuber, Ngoc Thang Vu:
Investigations on End- to-End Audiovisual Fusion. ICASSP 2018: 3041-3045 - [c205]Sjoerd van Steenkiste, Michael Chang, Klaus Greff, Jürgen Schmidhuber:
Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions. ICLR (Poster) 2018 - [c204]Lukas Tuggener, Ismail Elezi, Jürgen Schmidhuber, Marcello Pelillo, Thilo Stadelmann:
DeepScores-A Dataset for Segmentation, Detection and Classification of Tiny Objects. ICPR 2018: 3704-3709 - [c203]Michael Wand, Tanja Schultz, Jürgen Schmidhuber:
Domain-Adversarial Training for Session Independent EMG-based Speech Recognition. INTERSPEECH 2018: 3167-3171 - [c202]Lukas Tuggener, Ismail Elezi, Jürgen Schmidhuber, Thilo Stadelmann:
Deep Watershed Detector for Music Object Recognition. ISMIR 2018: 271-278 - [c201]David Ha, Jürgen Schmidhuber:
Recurrent World Models Facilitate Policy Evolution. NeurIPS 2018: 2455-2467 - [c200]Imanol Schlag, Jürgen Schmidhuber:
Learning to Reason with Third Order Tensor Products. NeurIPS 2018: 10003-10014 - [i76]Jürgen Schmidhuber:
One Big Net For Everything. CoRR abs/1802.08864 (2018) - [i75]Sjoerd van Steenkiste, Michael Chang, Klaus Greff, Jürgen Schmidhuber:
Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions. CoRR abs/1802.10353 (2018) - [i74]David Ha, Jürgen Schmidhuber:
World Models. CoRR abs/1803.10122 (2018) - [i73]Lukas Tuggener, Ismail Elezi, Jürgen Schmidhuber, Marcello Pelillo, Thilo Stadelmann:
DeepScores - A Dataset for Segmentation, Detection and Classification of Tiny Objects. CoRR abs/1804.00525 (2018) - [i72]Michael Wand, Ngoc Thang Vu, Jürgen Schmidhuber:
Investigations on End-to-End Audiovisual Fusion. CoRR abs/1804.11127 (2018) - [i71]Lukas Tuggener, Ismail Elezi, Jürgen Schmidhuber, Thilo Stadelmann:
Deep Watershed Detector for Music Object Recognition. CoRR abs/1805.10548 (2018) - [i70]David Ha, Jürgen Schmidhuber:
Recurrent World Models Facilitate Policy Evolution. CoRR abs/1809.01999 (2018) - [i69]Imanol Schlag, Jürgen Schmidhuber:
Learning to Reason with Third-Order Tensor Products. CoRR abs/1811.12143 (2018) - 2017
- [j67]Varun Raj Kompella, Marijn F. Stollenga, Matthew D. Luciw, Jürgen Schmidhuber:
Continual curiosity-driven skill acquisition from high-dimensional video inputs for humanoid robots. Artif. Intell. 247: 313-335 (2017) - [j66]Klaus Greff, Rupesh Kumar Srivastava, Jan Koutník, Bas R. Steunebrink, Jürgen Schmidhuber:
LSTM: A Search Space Odyssey. IEEE Trans. Neural Networks Learn. Syst. 28(10): 2222-2232 (2017) - [c199]Klaus Greff, Rupesh Kumar Srivastava, Jürgen Schmidhuber:
Highway and Residual Networks learn Unrolled Iterative Estimation. ICLR (Poster) 2017 - [c198]Klaus Greff, Sjoerd van Steenkiste, Jürgen Schmidhuber:
Neural Expectation Maximization. ICLR (Workshop) 2017 - [c197]Julian Georg Zilly, Rupesh Kumar Srivastava, Jan Koutník, Jürgen Schmidhuber:
Recurrent Highway Networks. ICML 2017: 4189-4198 - [c196]Michael Wand, Jürgen Schmidhuber:
Improving Speaker-Independent Lipreading with Domain-Adversarial Training. INTERSPEECH 2017: 3662-3666 - [c195]Klaus Greff, Sjoerd van Steenkiste, Jürgen Schmidhuber:
Neural Expectation Maximization. NIPS 2017: 6691-6701 - [c194]Klaus Greff, Aaron Klein, Martin Chovanec, Frank Hutter, Jürgen Schmidhuber:
The Sacred Infrastructure for Computational Research. SciPy 2017: 49-56 - [r1]Jürgen Schmidhuber:
Deep Learning. Encyclopedia of Machine Learning and Data Mining 2017: 338-348 - [i68]Michael Wand, Jürgen Schmidhuber:
Improving Speaker-Independent Lipreading with Domain-Adversarial Training. CoRR abs/1708.01565 (2017) - [i67]Klaus Greff, Sjoerd van Steenkiste, Jürgen Schmidhuber:
Neural Expectation Maximization. CoRR abs/1708.03498 (2017) - [i66]