On the importance of initialization and momentum in deep learning
Impact in
Classified as
- Journal
- International Conference on Machine Learning
In The Last Decade
doi.org/w3880520 →Countries where authors are citing On the importance of initialization and momentum in deep learning
This map shows the geographic impact of On the importance of initialization and momentum in deep learning. 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 On the importance of initialization and momentum in deep learning with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites On the importance of initialization and momentum in deep learning more than expected).
Fields of papers citing On the importance of initialization and momentum in deep learning
This network shows the impact of On the importance of initialization and momentum in deep learning. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the On the importance of initialization and momentum in deep learning.
About On the importance of initialization and momentum in deep learning
This paper, published in 2013, received 1.9k indexed citations . Written by Ilya Sutskever, James Martens, George E. Dahl and Geoffrey E. Hinton covering the research area of Artificial Intelligence and Computer Vision and Pattern Recognition. It is primarily cited by scholars working on Artificial Intelligence (942 citations), Computer Vision and Pattern Recognition (783 citations), Electrical and Electronic Engineering (173 citations), Signal Processing (163 citations) and Computational Mechanics (139 citations). Published in International Conference on Machine Learning.
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/w3880520.