Thomas Michalke, Robert Kastner, Michael Herbert, Jannik Fritsch, Christian Goerick , "Adaptive Multi-Cue Fusion for Robust Detection of Unmarked Inner-City Streets", IEEE Intelligent Vehicles Symposium (IV), 2009.
Cem Karaoguz, Mark Dunn, Tobias Rodemann, Christian Goerick , "Online Adaptation of Gaze Fixation for a Stereo-Vergence System with Foveated Vision", International Conference on Advanced Robotics (ICAR), 2009.
AbstractIn active vision systems, which direct their gaze to different visual targets in their environment, targets are represented in image coordinates and commands by which the gaze direction is changed are represented in motor coordinates. This requires knowledge of the mapping between two coordinate frames. In this work we present a robust mechanism that learns such a mapping. The mechanism can be applied to any active vision system performing arbitr...
Holger Brandl , "A computational model for unsupervised childlike speech acquisition", Universität Bielefeld, Technische Fakultät, 2009.
AbstractSpeech understanding requires the ability to parse spoken utterances into words. But this ability is not innate and needs to be developed by infants within the first years of their life. So far al- most all computational speech processing systems neglected this bootstrapping process. Here we propose a model for early infant speech structure acquisition implemented as layered architecture comprising phones, syllables and words. Our model processes...
Alexander Denecke, Heiko Wersing, Jochen Steil, Edgar Körner , "Incremental Figure-Ground Segmentation using localized adaptive metrics in LVQ", Proc. 7th International Workshop on Self-Organizing Maps (WSOM), 2009.
AbstractAbstract. Vector quantization methods are confronted with a model selection problem, namely the number of prototypical feature representatives to model each class. In this paper we present an incremental learning scheme in the context of figure-ground segmentation. In presence of local adaptive metrics and supervised noisy information we use a parallel evaluation scheme combined with a local utility function to organize a learning vector quantiza...
Martin Ernst Heckmann, Holger Brandl, Xavier Domont, Miguel Vaz, Jens Schmüdderich, Bram Bolder, Frank Joublin, Christian Goerick , "Language Acquisition Embedded into Tutor-Robot Interaction", Proc. ACORNS Workshop Computational Models of Language Evolution, Acquisition and Processing, 2009.
AbstractChildren acquire language to a large extend in the interaction with their caregivers. Inspired by this observation we develop computational models and artifacts for the acquisition of language in an interactive scenario. The artifact bootstraps its representations with little a priori knowledge and can be taught by a human tutor. In this framework we investigate different aspects of the speech acquisition process. This encompasses the learning of...
Martin Ernst Heckmann, Xavier Domont, Frank Joublin, Christian Goerick , "Combining Auditory Inspirations and Hierarchical Feature Extraction for Robust Speech Recognition", Proceedings of NAG-DAGA: International Conference on Acoustics, 2009.
AbstractWe present speech features inspired by the processing in the auditory periphery and the receptive fields found in the auditory cortex. They have a hierarchical organization and jointly evaluate variations in the spectro-temporal domain. This is why we termed them Hierarchical Spectro-Temporal (HIST) features. For their calculation we apply a Gammatone filterbank to transform the signal into the spectral domain. In a preprocessing based on local c...
Friedemann Pulvermüller and Andreas Knoblauch , "Discrete combinatorial circuits emerging in neural networks: A mechanism for rules of grammar in the human brain?", Neural Networks, vol. 22, pp. 161–172, 2009.
Tobias Rodemann, Frank Joublin, Christian Goerick , "Audio Proto Objects for Improved Sound Localization", IEEE-RSJ International Conference on Intelligent Robot and Systems (IROS 2009), 2009.
AbstractIn this article we present a new framework for auditory processing that combines feature extraction and grouping processes to form what we call audio proto objects. These proto objects combine an arbitrary number of audio features in a compact representation that allows a more precise sound localization and also better interfacing to behavior-control in robotics. We compare our standard sound localization system with the new approach in several s...
Matthew Howard , "Learning Control Policies from Constrained Motion", University of Edinburgh, 2009.
AbstractMany everyday human skills can be framed in terms of performing some task subject to constraints imposed by the task or the environment. Constraints are usually unobservable and frequently change between contexts. In this thesis, we explore the problem of learning control policies from data containing variable, dynamic and non-linear constraints on motion. We show that an effective approach for doing this is to learn the unconstrained policy in a...
Thomas H Weisswange, Constantin Rothkopf, Tobias Rodemann, Jochen Triesch , "Can reinforcement learning explain the development of causal inference in multisensory integration?", Proceedings of the IEEE 8th International Conference on Development and Learning (ICDL), 2009.
AbstractBayesian inference techniques have been used to understand the performance of human subjects on a large number of sensory tasks. Particularly, it has been shown that humans integrate sensory inputs from multiple cues in an optimal way in many conditions. Recently it has also been proposed that causal inference [1] can well describe the way humans select the most plausible model for a given input. It is still unclear how those problems are solved ...