Local minima and plateaus pose a serious problem in learning of neural networks. We investigate the hierarchical geometric structure of the parameter space of three-layer perceptr...
Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
In February 2002, more than 50 leaders in the information assurance field warned the President of the United States of a national strategic vulnerability in the country’s inform...
The need for early detection of temporal events from sequential data arises in a wide spectrum of applications ranging from human-robot interaction to video security. While tempor...
Hidden Markov models assume that observations in time series data stem from some hidden process that can be compactly represented as a Markov chain. We generalize this model by as...