PhD Colloquium: Unsupervised Learning of Human-Object Interactions with Neural Network Self-Organization

27 November 2018

Abstract. The main goal of this thesis is the modeling of unsupervised learning architectures for the recognition of human-object interactions.

We apply hierarchies of growing self-organizing neural networks for processing and integrating relevant cues from body motion and the action’s context. We propose and evaluate two extensions of such architecture to account for motion and action anticipation. Finally, we investigate a learning mechanism that uses the classification error for modulating neural growth.

Tuesday, 27 November 2018, 16:00, Room D-220, Informatikum

Speaker: Luiza Mici, PhD Candidate at group WTM