Imagine two identical people receive exactly the same training on how to classify certain objects. Perhaps surprisingly, we show that one can then manipulate them into classifying...
Xiaojin Zhu, Bryan R. Gibson, Kwang-Sung Jun, Timo...
We present new results from a real-user evaluation of a data-driven approach to learning user-adaptive referring expression generation (REG) policies for spoken dialogue systems. ...
— When an agent observes its environment, there are two important characteristics of the perceived information. One is the relevance of information and the other is redundancy. T...
Zhihui Luo, David A. Bell, Barry McCollum, Qingxia...
Abstract. We formulate the problem of least squares temporal difference learning (LSTD) in the framework of least squares SVM (LS-SVM). To cope with the large amount (and possible ...
Researchers investigated differences in learner preferences for different types of instructional strategies and learning styles in online environments. Results suggested that matc...