Sciweavers

448 search results - page 48 / 90
» Abstraction in Predictive State Representations
Sort
View
DAGSTUHL
2007
14 years 11 months ago
A conceptual framework for (iterated) revision, update, and nonmonotonic reasoning
Abstract. This paper makes a foundational contribution to the discussions on the very nature of belief change operations. Belief revision and pdate are investigated within an abstr...
Gabriele Kern-Isberner
PKDD
2009
Springer
155views Data Mining» more  PKDD 2009»
15 years 4 months ago
Dynamic Factor Graphs for Time Series Modeling
Abstract. This article presents a method for training Dynamic Factor Graphs (DFG) with continuous latent state variables. A DFG includes factors modeling joint probabilities betwee...
Piotr W. Mirowski, Yann LeCun
CVPR
2007
IEEE
15 years 12 months ago
Discriminative Learning of Dynamical Systems for Motion Tracking
We introduce novel discriminative learning algorithms for dynamical systems. Models such as Conditional Random Fields or Maximum Entropy Markov Models outperform the generative Hi...
Minyoung Kim, Vladimir Pavlovic
SOFSEM
2004
Springer
15 years 3 months ago
Approaches Based on Markovian Architectural Bias in Recurrent Neural Networks
Recent studies show that state-space dynamics of randomly initialized recurrent neural network (RNN) has interesting and potentially useful properties even without training. More p...
Matej Makula, Michal Cernanský, Lubica Benu...
IJCAI
1997
14 years 11 months ago
Mental Tracking: A Computational Model of Spatial Development
Psychological experiments on children's development of spatial knowledge suggest experience at self-locomotion with visual tracking as important factors. Yet, the mechanism u...
Kazuo Hiraki, Akio Sashima, Steven Phillips