Projects per year
Abstract / Description of output
Recently, different machine learning methods have been introduced to tackle the challenging few-shot learning scenario that is, learning from a small labeled dataset related to a specific task. Common approaches have taken the form of meta-learning: learning to learn on the new problem given the old. Following the recognition that meta-learning is implementing learning in a multi-level model, we present a Bayesian treatment for the meta-learning inner loop through the use of deep kernels. As a result we can learn a kernel that transfers to new tasks; we call this Deep Kernel Transfer (DKT). This approach has many advantages: is straightforward to implement as a single optimizer, provides uncertainty quantification, and does not require estimation of task-specific parameters. We empirically demonstrate that DKT outperforms several state-of-the-art algorithms in few-shot classification, and is the state of the art for cross-domain adaptation and regression. We conclude that complex meta-learning routines can be replaced by a simpler Bayesian model without loss of accuracy.
Original language | English |
---|---|
Title of host publication | Advances in Neural Information Processing Systems 33 |
Publisher | Curran Associates Inc |
Pages | 16108-16118 |
Number of pages | 11 |
Volume | 33 |
Publication status | Published - 7 Dec 2020 |
Event | Thirty-Fourth Conference on Neural Information Processing Systems - Virtual Conference Duration: 6 Dec 2020 → 12 Dec 2020 https://nips.cc/Conferences/2020 |
Conference
Conference | Thirty-Fourth Conference on Neural Information Processing Systems |
---|---|
Abbreviated title | NeurIPS 2020 |
City | Virtual Conference |
Period | 6/12/20 → 12/12/20 |
Internet address |
Fingerprint
Dive into the research topics of 'Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels'. Together they form a unique fingerprint.Projects
- 1 Finished
-
Bonseyes - Platform for Open Development of Systems of Artificial Intelligence
1/12/16 → 31/01/20
Project: Research