1 Matching Annotations
  1. Oct 2020
    1. This is in stark contrast to the way that babies learn. They can recognize new objects after only seeing them a few times, and do so with very little effort and minimal external interaction. If ML’s greatest goal is to understand how humans learn, one must emulate the speed at which they do so. This direction of research is exemplified by a variety of techniques that may or may not fit into an existing paradigm; LeCun classified these tasks under the umbrella of “self-supervised learning.”

      Now "self-supervised" is hardly what babies do, when you see the importance of interactions in learning (see e.g. https://doi.org/10.1016/j.tics.2020.01.006 )