Search our Publications

Results

Claudius Gläser and Frank Joublin, "Perceptually Grounded Word Meaning Acquisition: A Computational Model", Proceedings of the Annual Meeting of the Cognitive Science Society (CogSci), pp. 1744–1749, 2010.

Abstract

We present a computational model for the incremental acquisition of word meanings. Inspired by Complementary Learning Systems theory the model comprises different components which are specifically tailored to satisfy the contradictory needs of (1) rapid memorization of word-scene associations and (2) statistical feature extraction to reveal word meanings. Both components are recurrently coupled to achieve a memory consolidation. This process refl...



Download Bibtex file Download PDF

Nicole Naue, Daniel Strüber, Ingo Fründ, Jeanette Schadow, Daniel Lenz, Stefan Rach, Ursula Körner, Christoph Herrmann, "Pattern reversal elicits stronger evoked and induced gamma-band responses than motion", NeuroImage, vol. 55, no. 2, pp. 808-817, 2010.

Abstract

Hitherto, it is unclear whether gamma-band responses (GBRs, ≈40 Hz) of the electroencephalogram are more strongly modulated by visual stimulation with moving or rather with static objects. Most results suggest that GBRs occur more consistently in response to motion. We measured the electroencephalogram of healthy subjects watching high contrast, achromatic gratings. Briefly after their onset, the gratings either started to move or reversed thei...



Download Bibtex file Download PDF

Gervasio Puertas, Jörg Bornschein, Marc Henniges, Jörg Lücke, "The Maximal Causes of Natural Scenes are Edge Filters", Advances in Neural Information Processing Systems, vol. 23, pp. 1939-1947, 2010.

Abstract

We study the application of a strongly non-linear generative model to image patches. As in standard approaches such as Sparse Coding or Independent Component Analysis, the mod el assumes a sparse prior with independent hidden variables. However, in the place where standard approaches use the sum to combine basis functions we use the maximum. To derive tractable approximations for parameter estimation we apply a novel approach based on variationa...



Download Bibtex file Download PDF

Matthias Platho, "Learning of sensory representations for task-dependent control of search processes", Learning of sensory representations for task-dependent control of search processes, University Mannheim, 2010.

Abstract

Fulfilling demanding tasks in complex, dynamic environments poses a tough challenge for nowadays systems. A system relying on visual information has to handle a lot of data concerning the environment, the task and relevant objects. In order to reduce the amount of data a compression method for object datasets is proposed, that aims for maintaining task performance. An object dataset comprises numerical representations of object features in differ...



Download Bibtex file Per Mail Request

Robert Kastner, Thomas Michalke, Jannik Fritsch, Christian Goerick, "Towards a Task Dependent Representation Generation for Scene Analysis", IEEE Intelligent Vehicles Symposium (IV), 2010.

Abstract

State-of-the-art advanced driver assistance systems (ADAS) typically focus on single tasks and therefore, have clearly defined functionalities. Although said ADAS functions (e.g. lane departure warning) show good performance, they lack the general ability to extract spatial relations of the environment. These spatial relations are required for scene analysis on a higher layer of abstraction, providing a new quality of scene understanding, e.g. fo...



Download Bibtex file Download PDF

Mathias Franzius and Heiko Wersing, "Learning Invariant Visual Shape Representations from Physics", ICANN (3), pp. 298-302, 2010.

Abstract

3D shape determines an object’s physical properties to a large degree. In this article, we introduce an autonomous learning system for categorizing 3D shape of simulated objects from single views. The system extends an unsupervised bottom-up learning architecture based on the slowness principle with top-down information derived from the physical behavior of objects. The unsupervised bottom-up learning leads to pose invariant representations. Sh...



Download Bibtex file Download PDF

Gökhan Ince, Kazuhiro Nakadai, Tobias Rodemann, Hiroshi Tsujino, Jun-ichi Imura, "Robust Ego Noise Suppression of a Robot", 2010.

Abstract

This paper describes an architecture that can enhance a robot with the capability of performing automatic speech recognition even while the robot is moving. The system consists of three blocks: (1) a multi-channel noise reduction block comprising consequent stages of microphone-array-based sound localization, geometric source separa- tion and post filtering, (2) a single-channel template subtraction block and (3) a speech recognition block. In th...



Download Bibtex file Download PDF

Raphael Golombek, Sebastian Wrede, Marc Hanheide, Martin Heckmann, "A Method for learning a Fault Detection Model from Component Communication Data in Robotic Systems", Proc. 7th IARP Workshop on Technical Challenges for Dependable Robots in Human Environments, 2010.

Abstract

A promising means to increase the dependability of a robotic system is to equip it with the ability to autonomously monitor it own system state and detect faults. In this contribution we propose a method for fault detection in robotic systems which exploits the concept of anomaly detection and learns a model based on dynamics in the system’s internal exchange of data. Learning a model reduces the need for expert system-knowledge and enables on-...



Download Bibtex file Download PDF

Daniel Dornbusch, Robert Haschke, Stefan Menzel, Heiko Wersing, "Finding Correlations in Multimodal Data Using Decomposition Approaches", European Symposium on Artificial Neural Networks (ESANN), pp. 253 – 258, 2010.

Abstract

In this paper, we propose the application of standard decomposition approaches to find local correlations in multimodal data. In a test scenario, we apply these methods to correlate the local shape of turbine blades with their associated aerodynamic flow fields. We compare several decomposition algorithms, i.e., k-Means, Principal Component Analysis, Non-negative Matrix Factorization and Non-Negative Sparse Coding, with regards to their efficienc...



Download Bibtex file Download PDF

Vitali Anselm, "Receding Horizon Control for Anticipatory Movement Generation of a Robot Arm", Technical University of Dortmund, Chair for Control and Systems Engineering, 2010.

Abstract

The focus of this diploma thesis is set on the trajectory adaptation for robots with regard to dynamical changing situations. The existing system, which generates the movements of the robot by a batch-approach with sequential flow, is improved in such way that it becomes a system with a reactive behaviour. This work deploys the concepts of a predictive control, namely of the Receding Horizon Control (RHC). Thereby, a prediction horizon and optimi...



Download Bibtex file Per Mail Request

1 ... 95 96 97 98 99 100 ... 146

Search