Second order derivatives for network pruning: Optimal Brain Surgeon
- Authors
- Babak HassibiDavid G. Stork
- Journal
- CaltechAUTHORS (California Institute of Technology)
In The Last Decade
doi.org/w72621988 →Countries where authors are citing Second order derivatives for network pruning: Optimal Brain Surgeon
This map shows the geographic impact of Second order derivatives for network pruning: Optimal Brain Surgeon. 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 Second order derivatives for network pruning: Optimal Brain Surgeon with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Second order derivatives for network pruning: Optimal Brain Surgeon more than expected).
Fields of papers citing Second order derivatives for network pruning: Optimal Brain Surgeon
This network shows the impact of Second order derivatives for network pruning: Optimal Brain Surgeon. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the Second order derivatives for network pruning: Optimal Brain Surgeon.
About Second order derivatives for network pruning: Optimal Brain Surgeon
This paper, published in 1992, received 838 indexed citations . Written by Babak Hassibi and David G. Stork covering the research area of Electrical and Electronic Engineering and Artificial Intelligence. It is primarily cited by scholars working on Artificial Intelligence (612 citations), Computer Vision and Pattern Recognition (417 citations) and Electrical and Electronic Engineering (78 citations). Published in CaltechAUTHORS (California Institute of Technology).
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/w72621988.