Backbone Freezing
Backbone Freezing is a continual learning strategy in which the parameters of the foundational layers of a neural network are immobilized during subsequent task learning to preserve previously acquired knowledge while enabling adaptation in shallower or task-specific layers.
4
Publications
109
Citations
18
Authors
9
Institutions
Publications per year
2017–2026
4
Variants
Parameter FreezingWeight Freezing
Parents
4
Ji Gwang Yu, Si Hyun Han, Ha Lim Lee et al. · Journal of Materials Chemistry C · 2019 · 36 citations
1–5 of 4
18
1
h-index
1
h-index
1
h-index
1
h-index
1
h-index
1–5 of 18
9
Sungkyunkwan University
Seoul, South Korea
1 h-index
4 publications
144 citations
Microsoft Research (India)
Bengaluru, India
1 h-index
7 publications
203 citations

Peking University
Beijing, China
1 h-index
7 publications
203 citations
Brain (Germany)
Zwingenberg, Germany
1 h-index
3 publications
78 citations
Google (United States)
Mountain View, United States
1 h-index
3 publications
78 citations
Arizona State University
Tempe, United States
1 h-index
3 publications
54 citations
LG Chem (South Korea)
Seoul, South Korea
1 h-index
1 publications
36 citations
Vitenparken
Ås, Norway
1 h-index
1 publications
36 citations
1–8 of 9
Conference · 2 publications · 44 citations
2
h-index
1 publications · 36 citations
1
h-index
Conference · 1 publications · 29 citations
1
h-index
Repository · 1 publications · 13 citations
1–4