667 search results - page 21 / 134 » Learning to Model Sequences Generated by Switching Distribut... |
148
click to vote
AMFG
2005
IEEE
15 years 9 months ago
2005
IEEE
We present a new framework to represent and analyze dynamic facial motions using a decomposable generative model. In this paper, we consider facial expressions which lie on a one d...
148
Voted
NPL
2007
15 years 3 months ago
2007
Autonomous mobile robots form an important research topic in the field of robotics due to their near-term applicability in the real world as domestic service robots. These robots ...
138
Voted
AAAI
2006
15 years 5 months ago
2006
We present an algorithm that derives actions' effects and preconditions in partially observable, relational domains. Our algorithm has two unique features: an expressive rela...
128
Voted
IEEEIAS
2007
IEEE
15 years 9 months ago
2007
IEEE
Generative models of pattern individuality attempt to represent the distribution of observed quantitative features, e.g., by learning parameters from a database, and then use such...
130
Voted
ICML
2007
IEEE
16 years 4 months ago
2007
IEEE
The supremacy of n-gram models in statistical language modelling has recently been challenged by parametric models that use distributed representations to counteract the difficult...