Abstract. While traditional approaches to machine learning are sensitive to highdimensional state and action spaces, this paper demonstrates how an indirectly encoded neurocontroll...
Abstract. Quantitative verification techniques are able to establish system properties such as "the probability of an airbag failing to deploy on demand" or "the exp...
The compression of video can reduce the accuracy of post-compression tracking algorithms. This is problematic for centralized applications such as traffic surveillance systems, wh...
Eren Soyak, Sotirios A. Tsaftaris, Aggelos K. Kats...
We consider a semi-supervised regression setting where we have temporal sequences of partially labeled data, under the assumption that the labels should vary slowly along a sequen...
Abstract. Policies are declarations of constraints on the behaviour of components within distributed systems, and are often used to capture norms within agent-based systems. A few ...
Murat Sensoy, Timothy J. Norman, Wamberto Weber Va...