Policy gradient methods for reinforcement learning avoid some of the undesirable properties of the value function approaches, such as policy degradation (Baxter and Bartlett, 2001...
Evan Greensmith, Peter L. Bartlett, Jonathan Baxte...
In order to work well, many computer vision algorithms require that their parameters be adjusted according to the image noise level, making it an important quantity to estimate. W...
Ce Liu, William T. Freeman, Richard Szeliski, Sing...
This paper presents a novel approach for estimating the flow fields of dynamic temporal textures whose motion differs radically from that of rigid bodies. Our approach is based o...
David Edwards, Johnny T. Chang, Lin Shi, Yizhou Yu
The purpose of this paper is to quantify the efficiency with which Australian universities utilise their teaching resources. The study estimates the cost efficiency of 36 universi...
—Discriminative Training (DT) methods for acoustic modeling, such as MMI, MCE, and SVM, have been proved effective in speaker recognition. In this paper we propose a DT method fo...