Abstract: Web services are increasingly used to integrate heterogeneous and autonomous applications in cross-organizational cooperations. A key problem is to support a high executi...
This paper introduces GNARL, an evolutionary program which induces recurrent neural networks that are structurally unconstrained. In contrast to constructive and destructive algor...
Gregory M. Saunders, Peter J. Angeline, Jordan B. ...
In this paper we present an efficient algorithm for compile-time scheduling and clustering of parallel programs onto parallel processing systems with distributed memory, which is ...
In this paper we discuss computational complexity and risk averse approaches to two and multistage stochastic programming problems. We argue that two stage (say linear) stochastic ...
We present an actor-critic scheme for reinforcement learning in complex domains. The main contribution is to show that planning and I/O dynamics can be separated such that an intra...
Pedro Alejandro Ortega, Daniel Alexander Braun, Si...