ICMLA
2010
13 years 9 months ago
2010
Abstract--In the Relational Reinforcement learning framework, we propose an algorithm that learns an action model allowing to predict the resulting state of each action in any give...
ICMLA
2010
13 years 10 months ago
2010
Finding the location of binding sites in DNA is a difficult problem. Although the location of some binding sites have been experimentally identified, other parts of the genome may ...
ICMLA
2010
13 years 10 months ago
2010
Abstract--In this paper we propose a probabilistic classification algorithm with a novel Dynamic Time Warping (DTW) kernel to automatically recognize flight calls of different spec...
ICMLA
2010
13 years 10 months ago
2010
Ordinal classification is a form of multi-class classification where there is an inherent ordering between the classes, but not a meaningful numeric difference between them. Althou...
ICMLA
2010
13 years 10 months ago
2010
Abstract--Clinical electroencephalography (EEG) is routinely used to monitor brain function in critically ill patients, and specific EEG waveforms are recognized by clinicians as s...
ICMLA
2010
13 years 10 months ago
2010
Abstract-- Policy Gradients with Parameter-based Exploration (PGPE) is a novel model-free reinforcement learning method that alleviates the problem of high-variance gradient estima...
ICMLA
2010
13 years 10 months ago
2010
How can we get such reliable behavior from the mind when the brain is made up of such unreliable elements as neurons? We propose that the answer is related to the emergence of stab...
ICMLA
2010
13 years 10 months ago
2010
Abstract--We study how to effectively integrate reinforcement learning (RL) and programming languages via adaptation-based programming, where programs can include non-deterministic...
ICMLA
2010
13 years 10 months ago
2010
Gene expression (microarray) data have been used widely in bioinformatics. The expression data of a large number of genes from small numbers of subjects are used to identify inform...
ICMLA
2010
13 years 10 months ago
2010
Reinforcement learning algorithms that employ neural networks as function approximators have proven to be powerful tools for solving optimal control problems. However, their traini...