The hard problem of meta-learning is what-to-learn.

Prat Y., Lamm E.

Binz et al. highlight the potential of meta-learning to greatly enhance the flexibility of AI algorithms, as well as to approximate human behavior more accurately than traditional learning methods. We wish to emphasize a basic problem that lies underneath these two objectives, and in turn suggest another perspective of the required notion of "meta" in meta-learning: knowing what to learn.

DOI

10.1017/S0140525X24000268

Type

Journal article

Publication Date

2024-09-23T00:00:00+00:00

Volume

47

Keywords

Humans, Learning, Artificial Intelligence, Algorithms

Permalink More information Close