Steps Toward Deep Kernel Methods from Infinite Neural Networks

08/20/2015
by   Tamir Hazan, et al.
0

Contemporary deep neural networks exhibit impressive results on practical problems. These networks generalize well although their inherent capacity may extend significantly beyond the number of training examples. We analyze this behavior in the context of deep, infinite neural networks. We show that deep infinite layers are naturally aligned with Gaussian processes and kernel methods, and devise stochastic kernels that encode the information of these networks. We show that stability results apply despite the size, offering an explanation for their empirical success.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset