A closer look at memorization in deep networks
Impact in
Classified as
- Journal
- Jagiellonian University Repository (Jagiellonian University)
In The Last Decade
doi.org/w10910583 →Countries where authors are citing A closer look at memorization in deep networks
This map shows the geographic impact of A closer look at memorization in deep networks. 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 A closer look at memorization in deep networks with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites A closer look at memorization in deep networks more than expected).
Fields of papers citing A closer look at memorization in deep networks
This network shows the impact of A closer look at memorization in deep networks. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the A closer look at memorization in deep networks.
About A closer look at memorization in deep networks
This paper, published in 2017, received 344 indexed citations . Written by Devansh Arpit, Stanisław Jastrzȩbski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder S Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville and Yoshua Bengio covering the research area of Artificial Intelligence. It is primarily cited by scholars working on Artificial Intelligence (276 citations), Computer Vision and Pattern Recognition (149 citations), Civil and Structural Engineering (25 citations), Radiology, Nuclear Medicine and Imaging (18 citations) and Industrial and Manufacturing Engineering (18 citations). Published in Jagiellonian University Repository (Jagiellonian 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.
This paper is also available at doi.org/w10910583.