ys when planning meant searching for a sequence of abstract actions that satisfied some symbolic predicate. Robots can now learn their own representations through statistical infe...
Studies have shown that users have great difficulty specifying their security and privacy policies in a variety of application domains. While machine learning techniques have succ...
Patrick Gage Kelley, Paul Hankes Drielsma, Norman ...
Convolutional networks have achieved a great deal of success in high-level vision problems such as object recognition. Here we show that they can also be used as a general method ...
Viren Jain, Joseph F. Murray, Fabian Roth, Sriniva...
Much of human knowledge is organized into sophisticated systems that are often called intuitive theories. We propose that intuitive theories are mentally represented in a logical ...
User feedback has proven very successful to query large multimedia databases. Due to the nature of the data representation and the mismatch between mathematical models and human p...