A Survey of Deep Meta-Learning

October 07, 2020 Β· The Cartographer Β· πŸ› Artificial Intelligence Review

πŸ“š THE CARTOGRAPHER: The Cartographer
Survey/review paper β€” maps the landscape rather than implementing a method.

"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 shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Machine Learning