In this paper, we concentrate on the expressive power of hierarchical structures in neural networks. Recently, the so-called SplitNet model was introduced. It develops a dynamic n...
Dimensionalitycurse and dimensionalityreduction are two issues that have retained highinterest for data mining, machine learning, multimedia indexing, and clustering. We present a...
Caetano Traina Jr., Agma J. M. Traina, Leejay Wu, ...
Many graphs used in real-world applications consist of nodes belonging to more than one category. We call such graph "multiplecategory graphs". Social networks are typic...
Takayuki Itoh, Chris Muelder, Kwan-Liu Ma, Jun Ses...
Regions which evolve over time are a significant aspect of many phenomena in geographic information science. Examples include areas in which a measured value (e.g. temperature, sal...
Matt Duckham, John G. Stell, Maria Vasardani, Mich...
We consider learning tasks where multiple target variables need to be predicted. Two approaches have been used in this setting: (a) build a separate single-target model for each ta...