54 research outputs found
Multimodal Segmentation of Object Manipulation Sequences with Product Models
No full textBarchunova A, Haschke R, Franzius M, Ritter H. Multimodal Segmentation of Object Manipulation Sequences with Product Models. Presented at the International Conference on Multimodal Interaction, Alicante
Identification of High-level Object Manipulation Operations from Multimodal Input
No full textBarchunova A, Franzius M, Pardowitz M, Ritter H. Identification of High-level Object Manipulation Operations from Multimodal Input. Presented at the IASTED International Conferences on Automation, Control, and Information Technology
Slowness and Sparseness for Unsupervised Learning of Spatial and Object Codes from Naturalistic Data
No full textDiese Doktorarbeit führt ein hierarchisches Modell für das unüberwachte Lernen aus quasi-natürlichen Videosequenzen ein. Das Modell basiert auf den Lernprinzipien der Langsamkeit und Spärlichkeit, für die verschiedene Ansätze und Implementierungen vorgestellt werden. Eine Vielzahl von Neuronentypen im Hippocampus von Nagern und Primaten kodiert verschiedene Aspekte der räumlichen Umgebung eines Tieres. Dazu gehören Ortszellen (place cells), Kopfrichtungszellen (head direction cells), Raumansichtszellen (spatial view cells) und Gitterzellen (grid cells). Die Hauptergebnisse dieser Arbeit basieren auf dem Training des hierarchischen Modells mit Videosequenzen aus einer Virtual-Reality-Umgebung. Das Modell reproduziert die wichtigsten räumlichen Codes aus dem Hippocampus. Die Art der erzeugten Repräsentationen hängt hauptsächlich von der Bewegungsstatistik des simulierten Tieres ab. Das vorgestellte Modell wird außerdem auf das Problem der invaranten Objekterkennung angewandt, indem Videosequenzen von simulierten Kugelhaufen oder Fischen als Stimuli genutzt wurden. Die resultierenden Modellrepräsentationen erlauben das unabhängige Auslesen von Objektidentität, Position und Rotationswinkel im Raum.This thesis introduces a hierarchical model for unsupervised learning from naturalistic video sequences. The model is based on the principles of slowness and sparseness. Different approaches and implementations for these principles are discussed. A variety of neuron classes in the hippocampal formation of rodents and primates codes for different aspects of space surrounding the animal, including place cells, head direction cells, spatial view cells and grid cells. In the main part of this thesis, video sequences from a virtual reality environment are used for training the hierarchical model. The behavior of most known hippocampal neuron types coding for space are reproduced by this model. The type of representations generated by the model is mostly determined by the movement statistics of the simulated animal. The model approach is not limited to spatial coding. An application of the model to invariant object recognition is described, where artificial clusters of spheres or rendered fish are presented to the model. The resulting representations allow a simple extraction of the identity of the object presented as well as of its position and viewing angle
Geotextilien im Wasserbau: Prüfung, Anwendung, Bewährung
No full textDie vorliegende Arbeit ist ein Beitrag zur Anwendung von Geotextilien im Erd- und Wasserbau mit der speziellen Behandlung der Problemkreise Prüfverfahren, filtertechnische Bemessung und Langzeitbeständigkeit von Geotextilien. Die Arbeit verbindet theoretische und praktische Vorgaben aus dem Bauingenieurwesen, der Textilindustrie und der Kunststoffchemie im Hinblick auf den Informationsbedarf des anwendenden Bauingenieurs.KWP-collectio
Learning of Object Manipulation Operations from Continuous Multimodal Input
No full textGroßekathöfer U, Barchunova A, Haschke R, Hermann T, Franzius M, Ritter H. Learning of Object Manipulation Operations from Continuous Multimodal Input. In: IEEE/RAS International Conference on Humanoid Robots 2011. 2011.In this paper we propose an approach for identification of high-level object manipulation operations within a continuous multimodal time-series. We focus on a multimodal approach for robust recognition of action primitive data. Our procedure combines an unsupervised Bayesian multimodal segmentation with a supervised machine learning approach. We briefly outline (1) the unsupervised segmentation and selection of uni- and bi-manual manipulation primitives developed in our previous work. We show (2) an application of the ordered means models to classification of estimated segments. To assess the performance of our approach, we compare the computed labels to the ground truth acquired during the data recording. In our experiments we examined the robustness of the procedure on two different sets of segments: full length (≈ 95% overlap with the ground truth on average), partial length (≈ 10% overlap with ground truth on average). We have achieved a cross validation rate of ≈ 0.95 and recognition accuracy of ≈ 0.97 for full length and ≈ 0.84 for partial length test sets
Slowness and sparseness lead to place, head-direction, and spatial-view cells.
No full textWe present a model for the self-organized formation of place cells, head-direction cells, and spatial-view cells in the hippocampal formation based on unsupervised learning on quasi-natural visual stimuli. The model comprises a hierarchy of Slow Feature Analysis (SFA) nodes, which were recently shown to reproduce many properties of complex cells in the early visual system []. The system extracts a distributed grid-like representation of position and orientation, which is transcoded into a localized place-field, head-direction, or view representation, by sparse coding. The type of cells that develops depends solely on the relevant input statistics, i.e., the movement pattern of the simulated animal. The numerical simulations are complemented by a mathematical analysis that allows us to accurately predict the output of the top SFA layer
- …
