Gradient-based Meta-learning with Learned Layerwise Metric and Subspace
- Title
- Gradient-based Meta-learning with Learned Layerwise Metric and Subspace
- Authors
- 이윤호
- Date Issued
- 2018
- Publisher
- 포항공과대학교
- Abstract
- Deep learning has been tremendously successful in many difficult tasks including
image classification and game-playing. However, deep networks require
copious amounts of data in order to achieve such performance. Meta-learning
methods have recently gained attention in this context as a way to remedy this
dependence on large datasets.
Gradient-based meta-learning methods leverage gradient descent to learn
the commonalities among various tasks. While previous such methods have been
successful in meta-learning tasks, they resort to simple gradient descent during
meta-testing. Our primary contribution is the MT-net , which enables the meta-
learner to learn on each layer’s activation space a subspace that the task-specific
learner performs gradient descent on. Additionally, a task-specific learner of
an MT-net performs gradient descent with respect to a meta-learned distance
metric, which warps the activation space to be more sensitive to task identity. We
demonstrate that the dimension of this learned subspace reflects the complexity of
the task-specific learner’s adaptation task, and also that our model is less sensitive
to the choice of initial learning rates than previous gradient-based meta-learning
methods. Our method achieves state-of-the-art or comparable performance on
few-shot classification and regression tasks.
- URI
- http://postech.dcollection.net/common/orgView/200000104867
https://oasis.postech.ac.kr/handle/2014.oak/93592
- Article Type
- Thesis
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.