Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
Learning the parts of objects by non-negative matrix factorization
19998.9k citationsDaniel D. Lee, H. Sebastian Seungprofile →
This map shows the geographic impact of Daniel D. Lee'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 Daniel D. Lee with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Daniel D. Lee more than expected).
This network shows the impact of papers produced by Daniel D. Lee. 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 Daniel D. Lee. The network helps show where Daniel D. Lee may publish in the future.
Co-authorship network of co-authors of Daniel D. Lee
This figure shows the co-authorship network connecting the top 25 collaborators of Daniel D. Lee.
A scholar is included among the top collaborators of Daniel D. Lee 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 Daniel D. Lee. Daniel D. Lee is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
All Works
20 of 20 papers shown
1.
Mitchell, Eric, et al.. (2020). Higher-Order Function Networks for Learning Composable 3D Object Representations. arXiv (Cornell University).2 indexed citations
Lynn, Christopher W. & Daniel D. Lee. (2016). Maximizing Influence in an Ising Network: A Mean-Field Optimal Solution. Neural Information Processing Systems. 29. 2487–2495.3 indexed citations
4.
Wang, Zhuo, Xue-Xin Wei, Alan A. Stocker, & Daniel D. Lee. (2016). Efficient Neural Codes under Metabolic Constraints. Neural Information Processing Systems. 29. 4619–4627.4 indexed citations
5.
Stocker, Alan A., et al.. (2013). Fisher-optimal neural population codes for high-dimensional diffeomorphic stimulus representations. Neural Information Processing Systems. 297–305.1 indexed citations
6.
Noh, Yung‐Kyun, Frank Park, & Daniel D. Lee. (2012). Diffusion Decision Making for Adaptive k-Nearest Neighbor Classification. Neural Information Processing Systems. 25. 1925–1933.5 indexed citations
7.
Crammer, Koby & Daniel D. Lee. (2010). Learning via Gaussian Herding. Neural Information Processing Systems. 23. 451–459.38 indexed citations
8.
Lin, Yuanqing, Jingdong Chen, Youngmoo E. Kim, & Daniel D. Lee. (2007). Blind channel identification for speech dereverberation using l1-norm sparse learning. Neural Information Processing Systems. 20. 921–928.27 indexed citations
9.
Ham, Jihun & Daniel D. Lee. (2006). Separating Pose and Expression in Face Images: A Manifold Learning Approach.5 indexed citations
10.
Lee, Daniel D., et al.. (2005). Beyond Gaussian Processes: On the Distributions of Infinite Networks. Neural Information Processing Systems. 18. 275–282.4 indexed citations
11.
Ham, Jihun, Daniel D. Lee, & Lawrence K. Saul. (2005). Semisupervised alignment of manifolds.. International Conference on Artificial Intelligence and Statistics.179 indexed citations
12.
Lin, Yuanqing & Daniel D. Lee. (2004). Bayesian Regularization and Nonnegative Deconvolution for Time Delay Estimation. ScholarlyCommons (University of Pennsylvania). 17. 809–816.8 indexed citations
13.
Sha, Fei, Lawrence K. Saul, & Daniel D. Lee. (2002). Multiplicative Updates for Nonnegative Quadratic Programming in Support Vector Machines. ScholarlyCommons (University of Pennsylvania). 15. 1065–1072.101 indexed citations
14.
Saul, Lawrence K. & Daniel D. Lee. (2001). Multiplicative Updates for Classification by Mixture Models. ScholarlyCommons (University of Pennsylvania). 14. 897–904.35 indexed citations
15.
Shriki, Oren, Haim Sompolinsky, & Daniel D. Lee. (2000). An Information Maximization Approach to Overcomplete and Recurrent Representations. Scholarly Commons (University of Pennsylvania). 13. 612–618.14 indexed citations
Lee, Daniel D. & Haim Sompolinsky. (1998). Learning a Continuous Hidden Variable Model for Binary Data. Neural Information Processing Systems. 11. 515–521.2 indexed citations
18.
Lee, Daniel D. & H. Sebastian Seung. (1997). A Neural Network Based Head Tracking System. neural information processing systems. 10. 908–914.2 indexed citations
19.
Lee, Daniel D. & H. Sebastian Seung. (1996). Unsupervised Learning by Convex and Conic Coding. neural information processing systems. 9. 515–521.71 indexed citations
20.
Cohen, David, Yao Hua Ooi, Paul Vernaza, & Daniel D. Lee. (1987). The University of Pennsylvania Robocup 2004 legged soccer team.1 indexed citations
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.