ICML
2005
IEEE
15 years 15 days ago
2005
IEEE
We study an approach for performing concurrent activities in Markov decision processes (MDPs) based on the coarticulation framework. We assume that the agent has multiple degrees ...
ICML
2005
IEEE
15 years 15 days ago
2005
IEEE
ICML
2005
IEEE
15 years 15 days ago
2005
IEEE
Classifiers that refrain from classification in certain cases can significantly reduce the misclassification cost. However, the parameters for such abstaining classifiers are ofte...
ICML
2005
IEEE
15 years 15 days ago
2005
IEEE
We examine the relationship between the predictions made by different learning algorithms and true posterior probabilities. We show that maximum margin methods such as boosted tre...
ICML
2005
IEEE
15 years 15 days ago
2005
IEEE
In this paper we describe a new method to reduce the complexity of support vector machines by reducing the number of necessary support vectors included in their solutions. The red...
ICML
2005
IEEE
15 years 15 days ago
2005
IEEE
In this paper, we compare both discriminative and generative parameter learning on both discriminatively and generatively structured Bayesian network classifiers. We use either ma...
ICML
2005
IEEE
15 years 15 days ago
2005
IEEE
Many real-world domains exhibit rich relational structure and stochasticity and motivate the development of models that combine predicate logic with probabilities. These models de...
ICML
2005
IEEE
15 years 15 days ago
2005
IEEE
The current framework of reinforcement learning is based on maximizing the expected returns based on scalar rewards. But in many real world situations, tradeoffs must be made amon...
ICML
2005
IEEE
15 years 15 days ago
2005
IEEE
This work provides a framework for learning sequential attention in real-world visual object recognition, using an architecture of three processing stages. The first stage rejects...
ICML
2005
IEEE
15 years 15 days ago
2005
IEEE
Chord progressions are the building blocks from which tonal music is constructed. Inferring chord progressions is thus an essential step towards modeling long term dependencies in...