This paper investigates several issues in the problem of detecting handwritten markings, or annotations, on printed documents. One issue is to define the appropriate units over wh...
We study a new data mining problem concerning the discovery of frequent agreement subtrees (FASTs) from a set of phylogenetic trees. A phylogenetic tree, or phylogeny, is an unorde...
This paper describes a novel Recursive Neural Network for adaptive processing of FacE Emotion Tree Structures (FEETS). We proposed to use tree structures to represent Gabor Face E...
We study tree languages that can be defined in 2. These are tree languages definable by a first-order formula whose quantifier prefix is , and simultaneously by a first-order for...
We propose a novel a framework for deriving approximations for intractable probabilistic models. This framework is based on a free energy (negative log marginal likelihood) and ca...