Energy-based Models
Energy-Based Models is a probabilistic machine learning framework that belongs to the class of undirected graphical models, distinguished by its specification of a scalar energy function whose minima correspond to the most probable states of the system, with probability densities derived via the Boltzmann distribution.
438
Publications
35.1K
Citations
1.4K
Authors
532
Institutions
Publications per year
2017–2026
198
438
Esteban Samaniego, Cosmin Anitescu, Somdatta Goswami et al. · Computer Methods in Applied Mechanics and Engineering · 2020 · 1.9K citations · Full text
Engineering, Computational Engineering, Computer Science +17
A Connection Between Score Matching and Denoising Autoencoders
Pascal Vincent · Neural Computation · 2011 · 980 citations
1–5 of 438
1.4K
13
h-index
13
h-index
9
h-index
8
h-index
8
h-index
1–5 of 1.4K
532
University of California, Los Angeles
Los Angeles, United States
15 h-index
58 publications
3.9K citations
Stanford University
Stanford, United States
11 h-index
22 publications
1.6K citations

University of Toronto
Toronto, Canada
10 h-index
20 publications
1K citations
Google (United States)
Mountain View, United States
10 h-index
22 publications
745 citations
University College London
London, United Kingdom
8 h-index
19 publications
736 citations

Centre National de la Recherche Scientifique
Paris, France
8 h-index
24 publications
674 citations
ETH Zurich
Zurich, Switzerland
7 h-index
10 publications
1.3K citations
Tsinghua University
Beijing, China
7 h-index
12 publications
403 citations
1–8 of 532
Repository · 62 publications · 3.6K citations
25
h-index
8 publications · 429 citations
8
h-index
Conference · 5 publications · 253 citations
5
h-index
TPAMI · 5 publications · 1.9K citations
5
h-index
5 publications · 171 citations
5
h-index
1–5