We propose a new approach for reinforcement learning in problems with continuous actions. Actions are sampled by means of a diffusion tree, which generates samples in the continuou...
Christian Vollmer, Erik Schaffernicht, Horst-Micha...
This paper proposes a definition, scope and topics of construction informatics--a discipline also known as `construction IT' or `communication and information technologies in...
Medical assessment of penetrating injuries is a difficult and knowledge-intensive task. Physical examination and computed tomographic (CT) imaging data must be combined with detai...
Daniel L. Rubin, Olivier Dameron, Yasser Bashir, D...
Convolution tree kernel has shown promising results in semantic role labeling (SRL). However, this kernel does not consider much linguistic knowledge in kernel design and only perf...
Min Zhang, Wanxiang Che, Guodong Zhou, AiTi Aw, Ch...
We propose a framework for the representation of visual knowledge in a robotic agent, with special attention to the understanding of dynamic scenes. According to our approach, und...
Antonio Chella, Marcello Frixione, Salvatore Gagli...