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

Journal: The Behavioral and brain sciences
Published Date:

Abstract

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.

Authors

  • Yosef Prat
    The Cohn Institute for History and Philosophy of Science and Ideas, Tel Aviv University, Tel Aviv, Israel yosefprat@gmail.com ehudlamm@post.tau.ac.ilhttps://www.ehudlamm.com.
  • Ehud Lamm
    The Cohn Institute for History and Philosophy of Science and Ideas, Tel Aviv University, Tel Aviv, Israel yosefprat@gmail.com ehudlamm@post.tau.ac.ilhttps://www.ehudlamm.com.