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.
Simultaneous Denoising, Deconvolution, and Demixing of Calcium Imaging Data
2016608 citationsEftychios A. Pnevmatikakis, Daniel Soudry et al.Neuronprofile →
Binarized Neural Networks
2016481 citationsItay Hubara, Daniel Soudry et al.arXiv (Cornell University)profile →
Author Peers
Peers are selected by citation overlap in the author's most active subfields.
citations ·
hero ref
This map shows the geographic impact of Daniel Soudry'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 Soudry with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Daniel Soudry more than expected).
This network shows the impact of papers produced by Daniel Soudry. 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 Soudry. The network helps show where Daniel Soudry may publish in the future.
Co-authorship network of co-authors of Daniel Soudry
This figure shows the co-authorship network connecting the top 25 collaborators of Daniel Soudry.
A scholar is included among the top collaborators of Daniel Soudry 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 Soudry. Daniel Soudry 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.
Michaeli, Tomer, et al.. (2021). The Implicit Bias of Minima Stability: A View from Function Space. Neural Information Processing Systems. 34.5 indexed citations
2.
Giladi, Niv, et al.. (2020). At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks?. arXiv (Cornell University).1 indexed citations
3.
Hoffer, Elad, et al.. (2020). Neural gradients are lognormally distributed: understanding sparse and quantized training.. arXiv (Cornell University).1 indexed citations
4.
Banner, Ron, Yury Nahshan, & Daniel Soudry. (2019). Post training 4-bit quantization of convolutional networks for rapid-deployment. Neural Information Processing Systems. 32. 7948–7956.175 indexed citations
5.
Gilboa, Dar, et al.. (2019). A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off. arXiv (Cornell University). 32. 7036–7046.1 indexed citations
Banner, Ron, Yury Nahshan, Elad Hoffer, & Daniel Soudry. (2018). ACIQ: Analytical Clipping for Integer Quantization of neural networks. arXiv (Cornell University).40 indexed citations
8.
Gunasekar, Suriya, Jason D. Lee, Daniel Soudry, & Nathan Srebro. (2018). Characterizing Implicit Bias in Terms of Optimization Geometry. International Conference on Machine Learning. 2932–2955.29 indexed citations
9.
Banner, Ron, Itay Hubara, Elad Hoffer, & Daniel Soudry. (2018). Scalable methods for 8-bit training of neural networks. arXiv (Cornell University). 31. 5145–5153.52 indexed citations
10.
Hoffer, Elad, et al.. (2018). Bayesian Gradient Descent: Online Variational Bayes Learning with Increased Robustness to Catastrophic Forgetting and Weight Pruning.. arXiv (Cornell University).1 indexed citations
11.
Hoffer, Elad, et al.. (2018). Norm matters: efficient and accurate normalization schemes in deep networks. Neural Information Processing Systems. 31. 2160–2170.16 indexed citations
12.
Karoly, Philippa J., Levin Kuhlmann, Daniel Soudry, et al.. (2018). Seizure pathways: A model-based investigation. PLoS Computational Biology. 14(10). e1006403–e1006403.41 indexed citations
13.
Hoffer, Elad, Itay Hubara, & Daniel Soudry. (2017). Train longer, generalize better: closing the generalization gap in large batch training of neural networks. Neural Information Processing Systems. 30. 1731–1741.48 indexed citations
Chklovskii, Dmitri B. & Daniel Soudry. (2012). Neuronal Spike Generation Mechanism as an Oversampling, Noise-shaping A-to-D converter. Neural Information Processing Systems. 25. 503–511.5 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.