Reusing or modifying known design concepts cannot meet new challenges for engineering systems. However, engineers can find inspiration outside their traditional domains in order to...
— We propose a method that takes observations of a random vector as input, and learns to segment each observation into two disjoint parts. We show how to use the internal coheren...
Abstract. Machine learning methods were successfully applied in recent years for detecting new and unseen computer viruses. The viruses were, however, detected in small virus loade...
Abstract. Imitation learning is an intuitive and easy way of programming robots. Instead of specifying motor commands, you simply show the robot what to do. This paper presents a m...
Recently researchers have introduced methods to develop reusable knowledge in reinforcement learning (RL). In this paper, we define simple principles to combine skills in reinforce...