Building machines that learn and think like people Lake et al., arXiv 2016
Pro-tip: if you’re going to try and read and write up a paper every weekday, it’s best not to pick papers that run to over 50 pages. When the paper is as interesting as « Building machines that learn and think like people » though, it’s a pleasure to take a little extra time. You may recall from Monday’s write-up of « AI and Life in 2030 » that alongside steady progress, I harbour a secret hope that we have one or more big breakthroughs over the next decade. Where might those breakthroughs come from? I’m sure we’ll be able to take on problems of increasing scale, but I suspect progress there will feel more incremental. The places where we could still make order-of-magnitude style improvements seem to be:
- Data efficiency – training a model to a certain level…
Voir l’article original 2 246 mots de plus
Papier de soi 