The paper presents an approach to using structural descriptions, obtained through a human-robot tutoring dialogue, as labels for the visual object models a robot learns. The paper...
Geert-Jan M. Kruijff, John D. Kelleher, Gregor Ber...
Decision trees are a widely used knowledge representation in machine learning. However, one of their main drawbacks is the inherent replication of isomorphic subtrees, as a result...
Christophe Mues, Bart Baesens, Craig M. Files, Jan...
Learning temporal graph structures from time series data reveals important dependency relationships between current observations and histories. Most previous work focuses on learn...
Abstract. Visual dictionary learning and base (binary) classifier training are two basic problems for the recently most popular image categorization framework, which is based on t...
Real world multiagent coordination problems are important issues for reinforcement learning techniques. In general, these problems are partially observable and this characteristic ...