Mixture Of Experts
Mixture of Experts is a type of ensemble learning model in which a gating network dynamically assigns input instances to specialized submodels, or "experts," each trained on distinct regions of the input space to improve overall predictive performance.
311
Publications
47.1K
Citations
1.1K
Authors
337
Institutions
Publications per year
2017–2026
114
311
Distilling the Knowledge in a Neural Network
Geoffrey E. Hinton, Oriol Vinyals · arXiv (Cornell University) · 2015 · 14K citations · Full text
Adaptive Mixtures of Local Experts
Robert A. Jacobs, Michael I. Jordan, Steven J. Nowlan et al. · Neural Computation · 1991 · 5K citations
Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts
Jiaqi Ma, Zhe Zhao, Xinyang Yi et al. · 2018 · 1.1K citations · Full text
1–5 of 311
1.1K
8
h-index
7
h-index
6
h-index
6
h-index
6
h-index
1–5 of 1.1K
337

University of Toronto
Toronto, Canada
11 h-index
20 publications
10.9K citations
The University of Texas at Austin
Austin, United States
9 h-index
19 publications
709 citations
Google (United States)
Mountain View, United States
9 h-index
49 publications
10.1K citations

Shahid Rajaee Teacher Training University
Tehran, Iran
8 h-index
16 publications
791 citations
Northwestern University
Evanston, United States
7 h-index
11 publications
605 citations
University of Kent
Canterbury, United Kingdom
7 h-index
12 publications
317 citations
Carnegie Mellon University
Pittsburgh, United States
6 h-index
13 publications
802 citations
Massachusetts Institute of Technology
Cambridge, United States
6 h-index
12 publications
13.9K citations
1–8 of 337
Repository · 32 publications · 15.3K citations
18
h-index
11 publications · 13.2K citations
11
h-index
9 publications · 567 citations
9
h-index
7 publications · 334 citations
7
h-index
6 publications · 638 citations
6
h-index
1–5