The learned parametric mixture method is presented for a canonical cost function based ICA model on linear mixture, with several new findings. First, its adaptive algorithm is fu...
We propose a class of graphical models appropriate for structure prediction problems where the model structure is a function of the output structure. Incremental Sigmoid Belief Ne...
Abstract. Sigmoidal or radial transfer functions do not guarantee the best generalization nor fast learning of neural networks. Families of parameterized transfer functions provide...
We variationally derive a thermodynamically consistent model for surface evolution under the influence of free adatoms. The resulting system of nonlinear partial differential equat...
straction is a useful tool for agents interacting with environments. Good state abstractions are compact, reuseable, and easy to learn from sample data. This paper and extends two...