Alexander Gepperth
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Alexander Gepperth has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
Thomas Hecht
U2IS, Flowers Team, Inria, Université Paris-Saclay
2 shared publications- Cem Karaoguz
ENSTA ParisTech, UIIS Lab University of Paris-Saclay, Palaiseau, France
1 shared publication - Mandar Gogate
School of Computing, Merchiston Campus, Edinburgh Napier University, Edinburgh EH10 5DT, UK
1 shared publication Stéphane Magand
Hochschule Ruhr West Lützowstraße 5 46236 Bottrop Germany
1 shared publicationThomas Kopinski
Hochschule Ruhr West Lützowstraße 5 46236 Bottrop Germany
1 shared publicationUwe Handmann
Hochschule Ruhr West Lützowstraße 5 46236 Bottrop Germany
1 shared publication
Latest Publications
- 13 August 2016
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 121-127
Computational Advantages of Deep Prototype-Based Learning
- 13 August 2016
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 121-127
Computational Advantages of Deep Prototype-Based Learning
- 14 March 2016
- Published by Springer Nature in Cognitive Computation
- Vol. 8 (5) , 806-817
A Generative Learning Approach to Sensor Fusion and Change Detection
- 14 March 2016
- Published by Springer Nature in Cognitive Computation
- Vol. 8 (5) , 806-817
A Generative Learning Approach to Sensor Fusion and Change Detection
- 9 March 2016
- Published by Springer Nature in Cognitive Computation
- Vol. 8 (5) , 924-934
A Bio-Inspired Incremental Learning Architecture for Applied Perceptual Problems
- 9 March 2016
- Published by Springer Nature in Cognitive Computation
- Vol. 8 (5) , 924-934
A Bio-Inspired Incremental Learning Architecture for Applied Perceptual Problems
- Open Access
A pragmatic approach to multi-class classification
We present a novel hierarchical approach to multi-class classification which is generic in that it can be applied to different classification models (e.g., support vector machines, perceptrons), and makes no explicit assumptions about the probabilistic structure of the problem as it is usually done in multi-class classification. By adding a cascade of additional classifiers, each of which receives the previous classifier's output in addition to regular input data, the approach harnesses unused information that manifests itself in the form of, e.g., correlations between predicted classes. Using multilayer perceptrons as a classification model, we demonstrate the validity of this approach by testing it on a complex ten-class 3D gesture recognition task.
Open AccessA pragmatic approach to multi-class classification
We present a novel hierarchical approach to multi-class classification which is generic in that it can be applied to different classification models (e.g., support vector machines, perceptrons), and makes no explicit assumptions about the probabilistic structure of the problem as it is usually done in multi-class classification. By adding a cascade of additional classifiers, each of which receives the previous classifier's output in addition to regular input data, the approach harnesses unused information that manifests itself in the form of, e.g., correlations between predicted classes. Using multilayer perceptrons as a classification model, we demonstrate the validity of this approach by testing it on a complex ten-class 3D gesture recognition task.
- 1 May 2013
- Published by Elsevier in Neural Networks
- Vol. 41, 39-50
Efficient online bootstrapping of sensory representations
- 1 May 2013
- Published by Elsevier in Neural Networks
- Vol. 41, 39-50
Efficient online bootstrapping of sensory representations