Sciweavers

3726 search results - page 473 / 746
» A structured definition of the modeling process
Sort
View
NIPS
1998
15 years 8 months ago
Risk Sensitive Reinforcement Learning
In this paper, we consider Markov Decision Processes (MDPs) with error states. Error states are those states entering which is undesirable or dangerous. We define the risk with re...
Ralph Neuneier, Oliver Mihatsch
CSL
2010
Springer
15 years 6 months ago
Bayesian update of dialogue state: A POMDP framework for spoken dialogue systems
This paper describes a statistically motivated framework for performing real-time dialogue state updates and policy learning in a spoken dialogue system. The framework is based on...
Blaise Thomson, Steve Young
ICPR
2004
IEEE
16 years 7 months ago
From Massively Parallel Image Processors to Fault-Tolerant Nanocomputers
Parallel processors such as SIMD computers have been successfully used in various areas of high performance image and data processing. Due to their characteristics of highly regula...
Jie Han, Pieter Jonker
SCALESPACE
2009
Springer
16 years 1 months ago
PDE-Driven Adaptive Morphology for Matrix Fields
Matrix fields are important in many applications since they are the adequate means to describe anisotropic behaviour in image processing models and physical measurements. A promin...
Bernhard Burgeth, Michael Breuß, Luis Pizarr...
MM
2009
ACM
177views Multimedia» more  MM 2009»
16 years 1 months ago
Transfer non-metric measures into metric for similarity search
Similarity search is widely used in multimedia retrieval systems to find the most similar ones for a given object. Some similarity measures, however, are not metric, leading to e...
Danzhou Liu, Kien A. Hua