Practical supervised learning scenarios involving subjectively evaluated data have multiple evaluators, each giving their noisy version of the hidden ground truth. Majority logic ...
Statistical user simulation is an efficient and effective way to train and evaluate the performance of a (spoken) dialog system. In this paper, we design and evaluate a modular da...
Adaptive walk on a fitness soundscape [7] is a new kind of interactive evolutionary computation for musical works. This system provides a virtual two-dimensional grid called a “...
Reiji Suzuki, Souichiro Yamaguchi, Martin L. Cody,...
Action modeling is an important skill for agents that must perform tasks in novel domains. Previous work on action modeling has focused on learning STRIPS operators in discrete, r...
1 Information technology (IT) has a tremendous impact on the discipline of accounting by introducing new ways of retrieving and processing information about performance deviations ...