Relational reinforcement learning (RRL) is a Q-learning technique which uses first order regression techniques to generalize the Qfunction. Both the relational setting and the Q-l...
In this work we present a novel approach for learning nonhomogenous textures without facing the unlearning problem. Our learning method mimics the human behavior of selective lear...
Abstract. The capability calculus is a framework for statically reasoning about program resources such as deallocatable memory regions. Fractional capabilities, originally proposed...
We present and evaluate a NIC-based network intrusion detection system. Intrusion detection at the NIC makes the system potentially tamper-proof and is naturally extensible to wor...
Matthew Eric Otey, Srinivasan Parthasarathy, Amol ...
Java is increasingly being used as a language and binary format for low power, embedded systems. Current software only approaches to Java execution do not always suit the type of ...