Abstract. Sigmoidal or radial transfer functions do not guarantee the best generalization nor fast learning of neural networks. Families of parameterized transfer functions provide...
The combination of evidence for Information Retrieval has been studied extensively in order to increase effectiveness. In this paper, we study the selective application of differe...
We present a new algorithm, GM-Sarsa(0), for finding approximate solutions to multiple-goal reinforcement learning problems that are modeled as composite Markov decision processe...
To assist the decision makers, we develop a new supply chain simulation software: Easy-SC, a Java-based tool that simplifies the supply chain simulation. In its current state of d...
As systems become more and more complex the use of automation tools becomes more important. Although automation is introduced to reduce human workload, improve situational awarene...