Unsupervised Representation Learning via Neural Activation Coding
Yookoon Park 1 Sangho Lee 2 Gunhee Kim 2 David M. Blei 1
Abstract
We present neural activation coding (NAC) as a
novel approach for learning deep representations
from unlabeled data for downstream applications.
We argue that the deep encoder should maximize
its nonlinear expressivity on the data for down-
stream predictors to take full advantage of its rep-
resentation pow ...


雷达卡




京公网安备 11010802022788号







