Neural Kernel Networks: a differentiable framework for compositional kernel learning. Like the Automatic Statistician, but trainable with gradient-based optimization rather than discrete search. By @ssydasheng et al.https://t.co/tMjjweiSBi pic.twitter.com/pv39kz9bDg
— Roger Grosse (@RogerGrosse) June 13, 2018
from Twitter https://twitter.com/RogerGrosse
June 12, 2018 at 06:32PM
via IFTTT
No comments:
Post a Comment