This paper presents a new technique, called Symbolic Program Decomposition (or SPD), for symbolic execution of multiple paths that is more scalable than existing techniques, which...
Abstract. Recently, the authors described a training method for a convolutional neural network of threshold neurons. Hidden layers are trained by by clustering, in a feed-forward m...
Johannes Fieres, Karlheinz Meier, Johannes Schemme...
A constrained agent is limited in the actions that it can take at any given time, and a challenging problem is to design policies for such agents to do the best they can despite t...
Abstract. Executable schema mappings between XML schemas are essential to support numerous data management tasks such as data exchange, data integration and schema evolution. The n...
Abstract. In adversarial classification tasks like spam filtering, intrusion detection in computer networks and biometric authentication, a pattern recognition system must not only...