For many types of machine learning algorithms, one can compute the statistically optimal" way to select training data. In this paper, we review how optimal data selection tec...
David A. Cohn, Zoubin Ghahramani, Michael I. Jorda...
In this paper we investigate a new architecture for recognizing human group actions in meetings. These group actions provide a basis that enables effective browsing and querying i...
A large class of problems requires real-time processing of complex temporal inputs in real-time. These are difficult tasks for state-of-the-art techniques, since they require captu...
Igal Raichelgauz, Karina Odinaev, Yehoshua Y. Zeev...
The authors previously proposed a self-organizing Hierarchical Cerebellar Model Articulation Controller (HCMAC) neural network containing a hierarchical GCMAC neural network and a ...
Abstract. A common practice to gain invariant features in object recognition models is to aggregate multiple low-level features over a small neighborhood. However, the differences ...