Bayesian Convolutional Deep Sets with Task-Dependent Stationary Prior
具有任务依赖平稳先验的贝叶斯卷积深度集合
Convolutional deep sets are the architecture of a deep neural network (DNN) that can model stationary stochastic process. This architecture uses the kernel smoother and the DNN to construct the translation equivariant functional representations, and thus reflects the inductive bias of the stationarity into DNN. However, since this architecture employs the kernel smoother known as the non-parametric model, it may produce ambiguous representations when the number of data…