We describe a programmable apparatus that uses a vibrating surface for sensorless, nonprehensile manipulation, where parts are systematically positioned and oriented without sensor...
In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...
This paper addresses the problem of similar image retrieval, especially in the setting of large-scale datasets with millions to billions of images. The core novel contribution is ...
—Many complex dynamical phenomena can be effectively modeled by a system that switches among a set of conditionally linear dynamical modes. We consider two such models: the switc...
Emily B. Fox, Erik B. Sudderth, Michael I. Jordan,...
In context-dependent acoustic modeling, it is important to strike a balance between detailed modeling and data sufficiency for robust estimation of model parameters. In the past,...