Global inducing point variational posteriors for Bayesian neural networks and
deep Gaussian processes
Sebastian W. Ober 1 Laurence Aitchison 2
Abstract specify a family of approximate posteriors over the weights,
with the classical approach being independent Gaussian dis-
We consider the optimal approximate posterior tributions over each individual weight (Hinton & Van Camp,
over the ...


雷达卡




京公网安备 11010802022788号







