Memory-augmented Meta-learning
Memory-Augmented Meta-Learning is a meta-learning framework that incorporates an explicit, external memory component to store and retrieve task-specific knowledge, thereby enhancing rapid adaptation to new tasks through improved information retention and generalization across episodes.
10
Publications
1.2K
Citations
53
Authors
23
Institutions
Publications per year
2017–2026
9
Parents
10
Solving Rubik's Cube with a Robot Hand
Ilge Akkaya, Marcin Andrychowicz, Maciek Chociej et al. · arXiv (Cornell University) · 2019 · 633 citations · Full text
1–5 of 10
53
2
h-index
2
h-index
2
h-index
2
h-index
2
h-index
1–5 of 53
23
Columbia University
New York, United States
1 h-index
2 publications
110 citations
Shandong University of Political Science and Law
Jinan, China
1 h-index
1 publications
44 citations
McGovern Institute for Brain Research
Cambridge, United States
1 h-index
1 publications
55 citations

Soochow University
Suzhou, China
1 h-index
4 publications
72 citations

Data61
Sydney, Australia
1 h-index
2 publications
28 citations
Hunan Police Academy
Changsha, China
1 h-index
2 publications
38 citations
Neusoft (China)
Shenyang, China
1 h-index
2 publications
36 citations

Hunan University
Changsha, China
1 h-index
1 publications
19 citations
1–8 of 23
Repository · 4 publications · 705 citations
4
h-index
1 publications · 18 citations
1
h-index
1 publications · 19 citations
1
h-index
1 publications · 55 citations
1
h-index
Conference · 1 publications · 125 citations
1
h-index
1–5