An algorithm for learning structural patterns given in terms of Attributed Relational Graphs (ARG's) is presented. The algorithm, based on inductive learning methodologies, pr...
We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...
Nonlinear dendritic processing appears to be a feature of biological neurons and would also be of use in many applications of artificial neural networks. This paper presents a mod...
This paper presents an extensive evaluation, on artificial datasets, of EDY, an unsupervised algorithm for automatically synthesizing a Structured Hidden Markov Model (S-HMM) from ...
Discriminative mapping transforms (DMTs) is an approach to robustly adding discriminative training to unsupervised linear adaptation transforms. In unsupervised adaptation DMTs ar...