Representation Learning
Representation Learning is a machine learning paradigm that belongs to the broader class of feature learning methods, distinguished by its focus on automatically discovering the optimal data representations required for feature detection or classification from raw inputs.
70.1K
Publications
7.6M
Citations
135.6K
Authors
10.7K
Institutions
Publications per year
2017–2026
51.1K
70.1K
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
1–5 of 70.1K
135.6K
92
h-index
83
h-index
81
h-index
European Organization for Nuclear Research, Switzerland
127 publications · 42.9K citations
78
h-index
73
h-index
1–5 of 135.6K
10.7K

Chinese Academy of Sciences
Beijing, China
210 h-index
5.9K publications
557.7K citations
Google (United States)
Mountain View, United States
204 h-index
2.5K publications
1.7M citations
Tsinghua University
Beijing, China
196 h-index
3.9K publications
501.9K citations
University of Chinese Academy of Sciences
Beijing, China
159 h-index
3.1K publications
285.1K citations
Carnegie Mellon University
Pittsburgh, United States
159 h-index
1.8K publications
260.9K citations
Nanyang Technological University
Singapore, Singapore
157 h-index
2.1K publications
352.8K citations
Chinese University of Hong Kong
Hong Kong, Hong Kong
147 h-index
1.3K publications
274.7K citations

Peking University
Beijing, China
145 h-index
2.2K publications
240K citations
1–8 of 10.7K
Repository · 8.2K publications · 967.1K citations
362
h-index
TPAMI · 1K publications · 312.2K citations
207
h-index
1.1K publications · 119.7K citations
160
h-index
Conference · 1.3K publications · 124.4K citations
156
h-index
1.9K publications · 114.6K citations
144
h-index
1–5