Urs Köster
Impact in
-
- Advanced Neural Network Applications
Papers in
-
- Neural dynamics and brain function 4
- Visual perception and processing mechanisms 3
-
- Neural Networks and Applications 2
- Computational Physics and Python Applications 1
- Co-authors
- Aapo Hyvärinen (3 shared papers)Jascha Sohl‐Dickstein (1 shared paper)Charles M. Gray (1 shared paper)Bruno A. Olshausen (1 shared paper)Tristan J. Webb (1 shared paper)Jonathan W. Pillow (1 shared paper)Jakob H. Macke (1 shared paper)Arjun K. Bansal (1 shared paper)
- Journals
- Network Computation in Neural Systems (1 paper)PLoS Computational Biology (1 paper)Nature Communications (1 paper)Neural Computation (1 paper)arXiv (Cornell University) (1 paper)
- Partner nations
- United StatesFinlandGermany
In The Last Decade
Urs Köster
8 papers receiving 228 citations
Peers
Comparison fields: 5 of 57
- Computational Mathematics 7
- Computer Vision and Pattern Recognition 97
- Signal Processing 46
- Cognitive Neuroscience 73
- Hardware and Architecture 21
Countries citing papers authored by Urs Köster
This map shows the geographic impact of Urs Köster's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Urs Köster with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Urs Köster more than expected).
Fields of papers citing papers by Urs Köster
This network shows the impact of papers produced by Urs Köster. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Urs Köster. The network helps show where Urs Köster may publish in the future.
Co-authors
The 20 scholars most cited alongside Urs Köster, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
| # | Work | ||
|---|---|---|---|
| 1 | Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks | 2017 | 76 |
| 2 | 2007 | 42 | |
| 3 | 2014 | 37 | |
| 4 | FastISA: A fast fixed-point algorithm for Independent Subspace Analysis | 2006 | 30 |
| 5 | Low-dimensional models of neural population activity in sensory cortical circuits | 2014 | 20 |
| 6 | 2010 | 17 | |
| 7 | 2024 | 8 | |
| 8 | Online Normalization for Training Neural Networks | 2019 | 6 |
About Urs Köster
Urs Köster is a scholar working on Cognitive Neuroscience, Artificial Intelligence, Statistical and Nonlinear Physics, Signal Processing and Biophysics, having authored 8 papers that have together received 236 indexed citations. Recurring topics across this work include Neural dynamics and brain function (4 papers), Visual perception and processing mechanisms (3 papers), Neural Networks and Applications (2 papers), Blind Source Separation Techniques (2 papers), Speech and Audio Processing (1 paper), Cell Image Analysis Techniques (1 paper), Computational Physics and Python Applications (1 paper) and Tensor decomposition and applications (1 paper). The work is most often cited by research in Computational Mathematics (7 citations), Computer Vision and Pattern Recognition (97 citations), Signal Processing (46 citations), Cognitive Neuroscience (73 citations) and Hardware and Architecture (21 citations). Urs Köster has collaborated with scholars based in United States, Finland and Germany. Frequent co-authors include Aapo Hyvärinen, Jascha Sohl‐Dickstein, Charles M. Gray, Bruno A. Olshausen, Tristan J. Webb, Jonathan W. Pillow, Jakob H. Macke, Arjun K. Bansal, Scott Gray and Oğuz H. Elibol. Their work appears in journals such as Network Computation in Neural Systems, PLoS Computational Biology, Nature Communications, Neural Computation and arXiv (Cornell University).
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.