Boris Hanin
- Artificial Intelligence
- Statistical and Nonlinear Physics
- Computer Vision and Pattern Recognition
- Cognitive Neuroscience
- Computational Theory and Mathematics
- Co-authors
- David RolnickAlexander ZlokapaSho YaidaDaniel A. RobertsJames B. SimonG. DezoortYasaman Bahri
- Topics
- Neural Networks and Applications (3 papers)Advanced Memory and Neural Computing (2 papers)Statistical Methods and Bayesian Inference (1 paper)
- Journals
- Proceedings of the National Academy of SciencesThe Annals of Applied ProbabilityJournal of Statistical Mechanics Theory and Experiment
- Partner nations
- United StatesSwitzerlandItaly
In The Last Decade
Boris Hanin
5 papers receiving 54 citations
Peers
Comparison fields: 5 of 33
- Artificial Intelligence 45
- Statistical and Nonlinear Physics 16
- Computer Vision and Pattern Recognition 10
- Cognitive Neuroscience 7
- Computational Theory and Mathematics 4
Countries citing papers authored by Boris Hanin
This map shows the geographic impact of Boris Hanin'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 Boris Hanin with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Boris Hanin more than expected).
Fields of papers citing papers by Boris Hanin
This network shows the impact of papers produced by Boris Hanin. 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 Boris Hanin. The network helps show where Boris Hanin may publish in the future.
Co-authorship network of co-authors of Boris Hanin
This figure shows the co-authorship network connecting the top 25 collaborators of Boris Hanin. A scholar is included among the top collaborators of Boris Hanin based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Boris Hanin. Boris Hanin is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | 0 | |
| 2 | 1 | |
| 3 | 9 | |
| 4 | 13 | |
| 5 | Deep ReLU Networks Have Surprisingly Few Activation Patterns | 28 |
| 6 | The Principles of Deep Learning Theory: An Effective Theory Approach to Understanding Neural Networks | 7 |
About Boris Hanin
Boris Hanin is a scholar working on Artificial Intelligence, Statistics and Probability and Computer Vision and Pattern Recognition, having authored 6 papers that have together received 58 indexed citations. Recurring topics across this work include Neural Networks and Applications (3 papers), Advanced Memory and Neural Computing (2 papers) and Statistical Methods and Bayesian Inference (1 paper). The work is most often cited by research in Artificial Intelligence (45 citations), Statistical and Nonlinear Physics (16 citations) and Structural Biology (1 citation). Boris Hanin has collaborated with scholars based in United States, Switzerland and Italy. Frequent co-authors include David Rolnick, Alexander Zlokapa, Sho Yaida, Daniel A. Roberts, James B. Simon, G. Dezoort and Yasaman Bahri. Their work appears in journals such as Proceedings of the National Academy of Sciences, The Annals of Applied Probability and Journal of Statistical Mechanics Theory and Experiment.
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.