Towards real-world meta-learning현실 세계에 적합한 메타러닝

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 118
  • Download : 0
We extend the conventional meta-learning frameworks to more realistic, practical, and large-scale learning scenarios. Firstly, realistic meta-learning assumes imbalances between classes and tasks, and also distributional shift between meta-training and meta-testing stage. Secondly, practical meta-learning aims to develop a versatile meta-knowledge that is agnostic to architectural differences. Lastly, we address large-scale meta-learning where a shared initialization or hyperparameter are efficiently learned over a heterogeneous set of many-shot tasks. In this paper, we show how we can efficiently and effectively address those challenging real-world meta-learning problems with various machine learning techniques such as variational inference, amortization, first-order approximation, Taylor approximation, Lipschitz assumption, and so on.
Advisors
Hwang, Sung Juresearcher황성주researcher
Description
한국과학기술원 :김재철AI대학원,
Publisher
한국과학기술원
Issue Date
2022
Identifier
325007
Language
eng
Description

학위논문(박사) - 한국과학기술원 : 김재철AI대학원, 2022.8,[vii, 74 p. :]

Keywords

Meta-learning▼aTask distribution▼aDistributional shift▼aImbalance▼aLarge-scale▼aFirst-order approximation▼aHyperparameter optimization▼aGradient alignment; 메타 학습▼a태스크 분포▼a분포 이동▼a불균형▼a대규모 학습▼a일차 근사법▼a하이퍼파라미터 최적화▼a그라디언트 정렬

URI
http://hdl.handle.net/10203/307930
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1007772&flag=dissertation
Appears in Collection
AI-Theses_Ph.D.(박사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0