| Ladder variational autoencoders CK Sønderby, T Raiko, L Maaløe, SK Sønderby, O Winther Advances in Neural Information Processing Systems, 3738-3746, 2016 | 426 | 2016 |
| Auxiliary deep generative models L Maaløe, CK Sønderby, SK Sønderby, O Winther Proceedings of the International Conference on Machine Learning, 2016 | 335 | 2016 |
| How to train deep variational autoencoders and probabilistic ladder networks CK Sønderby, T Raiko, L Maaløe, SK Sønderby, O Winther arXiv preprint arXiv:1602.02282, 2016 | 95 | 2016 |
| BIVA: A very deep hierarchy of latent variables for generative modeling L Maaløe, M Fraccaro, V Liévin, O Winther Advances in Neural Information Processing Systems, 2019 | 50 | 2019 |
| Recurrent spatial transformer networks SK Sønderby, CK Sønderby, L Maaløe, O Winther arXiv preprint arXiv:1509.05329, 2015 | 37 | 2015 |
| Improving semi-supervised learning with auxiliary deep generative models L Maaløe, CK Sønderby, SK Sønderby, O Winther NIPS Workshop on Advances in Approximate Bayesian Inference, 2015 | 27 | 2015 |
| Semi-supervised generation with cluster-aware generative models L Maaløe, M Fraccaro, O Winther NIPS Workshop on Advances in Approximate Bayesian Inference, 2017 | 26 | 2017 |
| Deep belief nets for topic modeling L Maaløe, M Arngren, O Winther ICML workshop on Knowledge-Powered Deep Learning for Text Mining, 2015 | 15 | 2015 |
| Utilizing Domain Knowledge in End-to-End Audio Processing TMS Tax, JLD Antich, H Purwins, L Maaløe NIPS workshop on machine learning for audio, 2017 | 6 | 2017 |
| Development and implementation of a PV performance monitoring system based on inverter measurements SV Spataru, A Gavriluta, D Sera, L Maaloe, O Winther 2016 IEEE Energy Conversion Congress and Exposition (ECCE), 1-7, 2016 | 6 | 2016 |
| Towards Hierarchical Discrete Variational Autoencoders V Liévin, A Dittadi, L Maaløe, O Winther NeurIPS Workshop on Advances in Approximate Bayesian Inference, 2019 | 4 | 2019 |
| On the Inductive Bias of Word-Character-Level Multi-Task Learning for Speech Recognition J Kremer, L Borgholt, L Maaløe NIPS Workshop on Interpretability and Robustness for Audio, Speech and Language, 2018 | 3 | 2018 |
| CaGeM: A Cluster Aware Deep Generative Model L Maaløe, M Fraccaro, O Winther NIPS Workshop on Advances in Approximate Bayesian Inferences, 2017 | 3 | 2017 |
| Condition Monitoring in Photovoltaic Systems by Semi-Supervised Machine Learning L Maaløe, O Winther, S Spataru, D Sera Energies 13 (3), 584, 2020 | 2 | 2020 |
| Do end-to-end speech recognition models care about context? L Borgholt, JD Havtorn, AS ˇZeljko Agic, L Maaløe, C Igel Proc. of Interspeech, 2020 | 1 | 2020 |
| MultiQT: Multimodal Learning for Real-Time Question Tracking in Speech J Drachmann Havtorn, J Latko, J Edin, L Borgholt, L Maaløe, L Belgrano, ... Association for Computational Linguistics, 2020 | | 2020 |
| Deep Generative Models for Semi-Supervised Machine Learning L Maaløe, O Winther, ON Nielsen, S Hauberg, U Paquet, R Turner DTU Compute, 2018 | | 2018 |
| Exploiting Nontrivial Connectivity for Automatic Speech Recognition M Paraschiv, L Borgholt, TMS Tax, M Singh, L Maaløe NIPS workshop on machine learning for audio, 2017 | | 2017 |
Ole WintherBiology, Univ of Copenhagen, Genomic Medicine, Rigshospitalet and Technical University of DenmarkVerified email at bio.ku.dk
