Nils Einecke and Julian Eggert,
"A Two-Stage Correlation Method for Stereoscopic Depth Estimation",
Proceedings of the International Conference on Digital Image Computing: Techniques and Applications, DICTA 2010, 2010.
Abstract
The computation of stereoscopic depth is an important field of computer vision. Although a large variety of algorithms has been developed, the traditional correlation-based versions of these algorithms are prevalent. This is mainly due to easy implementation and handling but also to the linear computational complexity, as compared to more elaborated algorithms based on diffusion processes, graph-cut or bilateral filtering. In this paper, we intro...
Download Bibtex file
Download PDF
Andreas Knoblauch, Günther Palm, Friedrich Sommer,
"Memory capacities for synaptic and structural plasticity.",
Neural Computation, vol. 22, no. 2, pp. 289–341, 2010.
Download Bibtex file
Download PDF
Gökhan Ince, Kazuhiro Nakadai, Tobias Rodemann, Yuji Hasegawa, Hiroshi Tsujino, Jun-ichi Imura,
"A Hybrid Framework for Ego Noise Cancellation of a Robot",
2010.
Abstract
Noise generated due to the motion of a robot is not desired, because it deteriorates the quality and intelligibility of the sounds recorded by robot-embedded microphones. It must be reduced or cancelled to achieve automatic speech recognition with a high performance. In this work, we divide ego-motion noise problem into three subdomains of arm, leg and head motion noise, depending on their complexity and intensity levels. We investigate methods t...
Download Bibtex file
Download PDF
Michael Gienger, Christian Goerick, Edgar Körner,
"Movement control in biologically plausible frames of reference",
ISR / Robotik 2010, 2010.
Abstract
Biological findings suggest that human movement is encoded in a variety of action-oriented reference frames. In contrast, robotics movement control is mostly formulated in traditional frames of reference, such as the world frame, or a robotfixed base frame. In this contribution, we will investigate these biological findings and propose a movement control formulation for redundant robots that are equipped with one or several effectors. We will sho...
Download Bibtex file
Download PDF
Stephan Kirstein, Heiko Wersing, Edgar Körner,
"Towards autonomous bootstrapping for life-long learning categorization tasks",
Proceedings International Joint Conference on Neural Networks, 2010.
Download Bibtex file
Download PDF
Till Steiner,
"Articial Evolutionary Development",
Thesis of the University Bielefeld, University Bielefeld, 2010.
Abstract
This thesis is situated in the field of Artificial Development coupled to evolutionary computation. I discuss the problem of finding a suitable abstraction level for the developmental process in engineering design. Here, suitable refers to the capability to produce non-trivial artifacts, while keeping the developmental process and its formation comprehensible. Throughout this thesis, I distinguish between two components of development: The first ...
Download Bibtex file
Per Mail Request
Volker Willert and Julian Eggert,
"Adaptive Velocity Tuning for Visual Motion Estimation",
European Symposium on Artificial Neural Networks (ESANN), 2010.
Abstract
In the brain, both neural processing dynamics as well as the perceptual interpretation of a stimulus can depend on sensory history. The underlying principle is a sensory adaptation to the statistics of the input collected over a certain amount of time, allowing the system to tune its detectors, e.g. by improving the sampling of the input space. Here we show how a generative formulation for the problem of visual motion estimation leads to an onlin...
Download Bibtex file
Download PDF
Irene Clemente, Martin Heckmann, Gerhard Sagerer, Frank Joublin,
"Multiple Sequence Alignment Based Bootstrapping for Improved Incremental Word Learning",
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2010.
Abstract
We investigate incremental word learning with few training exam- ples in a Hidden Markov Model (HMM) framework suitable for an interactive learning scenario with little prior knowledge. When using only a few training examples the initialization of the models is a cru- cial step. In the bootstrapping approach proposed, an unsupervised initialization of the parameters is performed, followed by the retrain- ing and construction of a new HMM using mu...
Download Bibtex file
Download PDF
Thomas Weisswange, Constantin Rothkopf, Tobias Rodemann, Jochen Triesch,
"Model averaging as a developmental outcome of reinforcement learning",
2010.
Abstract
To make sense of the world, humans have to rely on the information that they receive from their sensory systems. Due to noise on one side and redundancies on the other side, it is possible to improve estimates of the signal's causes by integrating over multiple sensors. In recent years it has been shown that humans do so in a way that can be matched by optimal Bayesian models (e.g. [1]). Such an integration is only beneficial for signals originat...
Download Bibtex file
Download PDF
Yaochu Jin and Jens Trommler,
"A Fitness-Independent Evolvability Measure for Evolutionary Developmental Systems",
Computational Intelligence in Bioinformatics and Computational Biology, 2010.
Download Bibtex file
Download PDF
1 ...
101 102 103 104
105 106 ...
151
