A Survey of Deep Meta-Learning
October 07, 2020 Β· The Cartographer Β· π Artificial Intelligence Review
"No code URL or promise found in abstract"
"Title-pattern auto-detect: A Survey of Deep Meta-Learning"
Evidence collected by the PWNC Scanner
Authors
Mike Huisman, Jan N. van Rijn, Aske Plaat
arXiv ID
2010.03522
Category
cs.LG: Machine Learning
Cross-listed
cs.AI,
stat.ML
Citations
389
Venue
Artificial Intelligence Review
Last Checked
1 day ago
Abstract
Deep neural networks can achieve great successes when presented with large data sets and sufficient computational resources. However, their ability to learn new concepts quickly is limited. Meta-learning is one approach to address this issue, by enabling the network to learn how to learn. The field of Deep Meta-Learning advances at great speed, but lacks a unified, in-depth overview of current techniques. With this work, we aim to bridge this gap. After providing the reader with a theoretical foundation, we investigate and summarize key methods, which are categorized into i)~metric-, ii)~model-, and iii)~optimization-based techniques. In addition, we identify the main open challenges, such as performance evaluations on heterogeneous benchmarks, and reduction of the computational costs of meta-learning.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Machine Learning
ποΈ
ποΈ
Transcended
ποΈ
ποΈ
Transcended
Continuous control with deep reinforcement learning
π
π
Old Age
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
π
π
Old Age
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
π
π
Old Age
SGDR: Stochastic Gradient Descent with Warm Restarts
ποΈ
ποΈ
Transcended