Abstract. In this thesis, we present a hybrid ensemble classifier approach for face detection and head-pose estimation.

Tuesday, 04 June 2019, 14:00, F-124, Informatikum

Speaker: Lukas Drude, University of Paderborn.

Abstract. Our minds make inferences that appear to go far beyond standard machine learning. Whereas people can learn richer representations and use them for a wider range of learning tasks, machine learning algorithms have been mainly...

The dates for the 2019 CML Symposium on Crossmodal Learning have been annouced. The event will take place from November 27 to November 29 at the University of Hamburg.

The fourth CML project summer school, including the joint DFG-NSFC project evaluation event, will take place from September 18 to September 25 2019 at Tsinghua University in Bejing, China.

Abstract. Inspired by human behaviour, we propose an embodied embedded cognition approach to improve automatic speech recognition with robots under noisy conditions using binaural sound source localisation.

Natural Language Understanding refers to NLP tasks that require a deep understanding of language, as opposed to shallow, surface-form processing. Most existing research in this area focuses on studying deep learning methods that require...

Abstract. We describe a new approach for incorporating prior knowledge into any machine learning algorithm. We aim at applications in physics and signal processing in which we know that certain operations must be embedded into the...

CML researcher Nikolaos Katzakis gave a tutorial on Deep Learning in IEEE Virtual Reality 2019 in Osaka on March 23. The tutorial also contained an introduction of the Cross-Modal Learning project and our research in the C6 subproject.

Real-life decisions involve the consolidation of inherent and acquired values. This study demonstrates that the congruence between inherent value and ac-quired reward influences the neural coding of learning rate. Neuroimaging results...