The results of a machine learning from user behavior can be thought of as a program, and like all programs, it may need to be debugged. Providing ways for the user to debug it mat...
Discriminative training has been a leading factor for improving automatic speech recognition (ASR) performance over the last decade. The traditional discriminative training, howev...
Abstract. We are interested in the relationship between learning efficiency and representation in the case of supervised neural networks for pattern classification trained by conti...
Cell tower triangulation is a popular technique for determining the location of a mobile device. However, cell tower triangulation methods require the knowledge of the actual loca...
Jie Yang, Alexander Varshavsky, Hongbo Liu, Yingyi...
This paper considers the least-square online gradient descent algorithm in a reproducing kernel Hilbert space (RKHS) without explicit regularization. We present a novel capacity i...