| Flexpoint: An adaptive numerical format for efficient training of deep neural networks U Köster, TJ Webb, X Wang, M Nassar, AK Bansal, WH Constable, ... arXiv preprint arXiv:1711.02213, 2017 | 152 | 2017 |
| FastISA: A fast fixed-point algorithm for independent subspace analysis. A Hyvärinen, U Köster EsANN, 371-376, 2006 | 73 | 2006 |
| Complex cell pooling and the statistics of natural images A Hyvärinen, U Köster Network: Computation in Neural Systems 18 (2), 81-100, 2007 | 68 | 2007 |
| Modeling higher-order correlations within cortical microcolumns U Köster, J Sohl-Dickstein, CM Gray, BA Olshausen PLoS Comput Biol 10 (7), e1003684, 2014 | 56 | 2014 |
| Low-dimensional models of neural population activity in sensory cortical circuits EW Archer, U Koster, JW Pillow, JH Macke Advances in Neural Information Processing Systems 27: 28th Conference on …, 2015 | 50 | 2015 |
| A two-layer ICA-like model estimated by score matching U Köster, A Hyvärinen International Conference on Artificial Neural Networks, 798-807, 2007 | 43 | 2007 |
| A two-layer model of natural stimuli estimated with score matching U Köster, A Hyvärinen Neural Computation 22 (9), 2308-2333, 2010 | 34 | 2010 |
| Estimating markov random field potentials for natural images U Köster, JT Lindgren, A Hyvärinen International Conference on Independent Component Analysis and Signal …, 2009 | 24 | 2009 |
| Online normalization for training neural networks V Chiley, I Sharapov, A Kosson, U Koster, R Reece, SS de la Fuente, ... arXiv preprint arXiv:1905.05894, 2019 | 12 | 2019 |
| Learning natural image structure with a horizontal product model U Köster, JT Lindgren, M Gutmann, A Hyvärinen International Conference on Independent Component Analysis and Signal …, 2009 | 11 | 2009 |
| Higher order correlations within cortical layers dominate functional connectivity in microcolumns U Köster, J Sohl-Dickstein, CM Gray, BA Olshausen arXiv preprint arXiv:1301.0050, 2013 | 10 | 2013 |
| Testing our conceptual understanding of V1 function U Köster, B Olshausen arXiv preprint arXiv:1311.0778, 2013 | 7 | 2013 |
| Pipelined Backpropagation at Scale: Training Large Models without Batches A Kosson, V Chiley, A Venigalla, J Hestness, U Köster arXiv preprint arXiv:2003.11666, 2020 | 1 | 2020 |
| Natural image statistics: Energy-based models estimated by score matching U Koster, A Hyvarinen 2009 International Workshop on Local and Non-Local Approximation in Image …, 2009 | 1 | 2009 |
| Adaptive Braking for Mitigating Gradient Delay A Venigalla, A Kosson, V Chiley, U Köster arXiv preprint arXiv:2007.01397, 2020 | | 2020 |
| Modeling neural population data U Köster, B Olshausen, C Gray 2013 Asilomar Conference on Signals, Systems and Computers, 358-361, 2013 | | 2013 |
| Sparse coding model captures V1 population response statistics to natural movies M Zhu, I Stevenson, U Köster, CM Gray, BA Olshausen, CJ Rozell BMC Neuroscience 14 (1), 1-1, 2013 | | 2013 |
| A probabilistic approach to the primary visual cortex U Köster Helsingin yliopisto, 2009 | | 2009 |
| Reversible Fixup Networks for Memory-Efficient Training V Thangarasa, CY Tsai, GW Taylor, U Köster | | |
Aapo HyvarinenUniversity of HelsinkiVerified email at helsinki.fi
