We present context-sensitive Multiple Task Learning, or csMTL as a method of inductive transfer. It uses additional contextual inputs along with other input features when learning ...
In this paper, we propose the application of standard decomposition approaches to find local correlations in multimodal data. In a test scenario, we apply these methods to correla...
Daniel Dornbusch, Robert Haschke, Stefan Menzel, H...
Consumers frequently rely on user-generated product reviews to guide purchasing decisions. Given the everincreasing volume of such reviews and variations in review quality, consum...
Intelligent software agents (agents) adhering to the action selection paradigm have only one primary task that they need accomplish at any given time: to choose their next action....
Ryan James McCall, Stan Franklin, David Friedlande...
We demonstrate the role of commonsense inference toward the modeling of qualitative notions of space and spatial change within a dynamic setup. The inference patterns are connecte...
The ability to mine data represented as a graph has become important in several domains for detecting various structural patterns. One important area of data mining is anomaly det...
William Eberle, Lawrence B. Holder, Jeffrey Graves
Factored planning methods aim to exploit locality to efficiently solve large but "loosely coupled" planning problems by computing solutions locally and propagating limit...
Eric Fabre, Loig Jezequel, Patrik Haslum, Sylvie T...
The utility of including loops in plans has been long recognized by the planning community. Loops in a plan help increase both its applicability and the compactness of representat...
Siddharth Srivastava, Neil Immerman, Shlomo Zilber...
Computing a good policy in stochastic uncertain environments with unknown dynamics and reward model parameters is a challenging task. In a number of domains, ranging from space ro...