Meta-learning Theory
Meta-Learning Theory is a formal academic construct that belongs to the category of theoretical frameworks in machine learning, specifically distinguished by its focus on principles and mechanisms that enable learning algorithms to acquire or improve their own learning processes across tasks through prior experience.
364
Publications
19.3K
Citations
1.2K
Authors
418
Institutions
Publications per year
2017–2026
247
Parents
364
Solving Rubik's Cube with a Robot Hand
Ilge Akkaya, Marcin Andrychowicz, Maciek Chociej et al. · arXiv (Cornell University) · 2019 · 633 citations · Full text
On First-Order Meta-Learning Algorithms
Alex Nichol, Joshua Achiam, John Schulman · arXiv (Cornell University) · 2018 · 544 citations · Full text
Learning to Learn Single Domain Generalization
Fengchun Qiao, L. Zhao, Xi Peng · 2020 · 449 citations
1–5 of 364
1.2K
10
h-index
9
h-index
7
h-index
6
h-index
6
h-index
1–5 of 1.2K
418
Google (United States)
Mountain View, United States
12 h-index
45 publications
1.5K citations
University of California, Berkeley
Berkeley, United States
11 h-index
22 publications
1.4K citations

Universidade do Porto
Porto, Portugal
11 h-index
17 publications
1.1K citations
Universidade de São Paulo
São Paulo, Brazil
10 h-index
20 publications
1.2K citations
Stanford University
Stanford, United States
9 h-index
19 publications
690 citations
Princeton University
Princeton, United States
7 h-index
9 publications
570 citations
Tsinghua University
Beijing, China
7 h-index
22 publications
2.1K citations
Nanyang Technological University
Singapore, Singapore
7 h-index
12 publications
868 citations
1–8 of 418
Repository · 65 publications · 3.5K citations
29
h-index
15 publications · 1.3K citations
13
h-index
9 publications · 417 citations
9
h-index
6 publications · 447 citations
6
h-index
6 publications · 211 citations
6
h-index
1–5