Abstract This paper proposes an approach for reducing the computational complexity of a model-predictive-control strategy for discrete-time hybrid systems with discrete inputs only...
Bostjan Potocnik, Gasper Music, Igor Skrjanc, Boru...
We derive cost formulae for three di erent parallelisation techniques for training supervised networks. These formulae are parameterised by properties of the target computer archit...
We present an emotion recognition system based on a probabilistic approach to adaptive processing of Facial Emotion Tree Structures (FETS). FETS are made up of localized Gabor fea...
Abstract. It has remained an open question whether there exist product unit networks with constant depth that have superlinear VC dimension. In this paper we give an answer by cons...
Conditional random fields (CRF) are widely used for predicting output variables that have some internal structure. Most of the CRF research has been done on structured classificati...