We develop a novel multi-class classification method based on output codes for the problem of classifying a sequence of amino acids into one of many known protein structural class...
Eugene Ie, Jason Weston, William Stafford Noble, C...
We report the results of a study on topic spotting in conversational speech. Using a machine learning approach, we build classifiers that accept an audio file of conversational hu...
Kary Myers, Michael J. Kearns, Satinder P. Singh, ...
Understanding high-dimensional real world data usually requires learning the structure of the data space. The structure maycontain high-dimensional clusters that are related in co...
—We propose an approach for improving object recognition and localization using spatial kernels together with instance embedding. Our approach treats each image as a bag of insta...
We propose a novel approach to experience collection for autonomous service robots performing complex activities. This approach enables robots to data for many learning problems at...