We present a method for learning a human understandable, executable model of an agent's behavior using observations of its interaction with the environment. By executable we ...
Andrew Guillory, Hai Nguyen, Tucker R. Balch, Char...
In this paper we present a method for learning classspecific
features for recognition. Recently a greedy layerwise
procedure was proposed to initialize weights of deep
belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...
Context is a key issue in interaction between human and computer, describing the surrounding facts that add meaning. In mobile computing research published the parameter location ...
Albrecht Schmidt, Michael Beigl, Hans-Werner Gelle...
We propose and analyze a distribution learning algorithm for variable memory length Markov processes. These processes can be described by a subclass of probabilistic nite automata...
Abstract. Automatic pattern classifiers that allow for on-line incremental learning can adapt internal class models efficiently in response to new information without retraining fr...