Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Scientists See Promise in Deep-Learning Programs. Parent comment
It's been awhile since I read the paper, but as I recall it involved training an unsupervised model layer-by-layer (training a layer, freezing the weights, then training another layer on top of it).
There are no comments on this comment yet.
It's been awhile since I read the paper, but as I recall it involved training an unsupervised model layer-by-layer (training a layer, freezing the weights, then training another layer on top of it).