119
click to vote
AAAI
2015
9 years 11 months ago
2015
The success of applying policy gradient reinforcement learning (RL) to difficult control tasks hinges crucially on the ability to determine a sensible initialization for the poli...
124
click to vote
AAAI
2015
9 years 11 months ago
2015
In this paper we model the problem of data linkage in Linked Data as a reasoning problem on possibly decentralized data. We describe a novel import-by-query algorithm that alterna...
114
click to vote
AAAI
2015
9 years 11 months ago
2015
Diseases such as autism, cardiovascular disease, and the autoimmune disorders are difficult to treat because of the remarkable degree of variation among affected individuals. Sub...
144
click to vote
AAAI
2015
9 years 11 months ago
2015
Object recognition systems can be unreliable when run in isolation depending on only image based features, but their performance can be improved when taking scene context into acc...
122
click to vote
AAAI
2015
9 years 11 months ago
2015
This paper raises the question of collective decision making under possibilistic uncertainty; We study four egalitarian decision rules and show that in the context of a possibilis...
116
click to vote
AAAI
2015
9 years 11 months ago
2015
Increased interest in web-based education has spurred the proliferation of online learning environments. However, these platforms suffer from high dropout rates due to lack of su...
103
click to vote
AAAI
2015
9 years 11 months ago
2015
Sparse learning has been proven to be a powerful technique in supervised feature selection, which allows to embed feature selection into the classification (or regression) proble...
AAAI
2015
9 years 11 months ago
2015
When scheduling tasks for field-deployable systems, our solutions must be robust to the uncertainty inherent in the real world. Although human intuition is trusted to balance rew...
AAAI
2015
9 years 11 months ago
2015
Module extraction—the task of computing a (preferably small) fragment M of an ontology T that preserves entailments over a signature Σ—has found many applications in recent y...
AAAI
2015
9 years 11 months ago
2015
Temperature Discovery Search (TDS) is a forward search method for computing or approximating the temperature of a combinatorial game. Temperature and mean are important concepts i...