Alexander Gepperth

40
Documents
Identifiants chercheurs

Présentation

Personal Information

Family status: married, 2children

Nationality: German

Experience in academia

5/2011 – present Tenured professor at „École Nationale Supérieure de Techniques
Avancées“ (Palaiseau, France)

Assignments: Teaching, research, supervision of theses,
organization of the specialization subject „intelligent vehicles“

Research focus: large-scale learning in intelligent vehicles

Industrial experience

02/2008 – 5/2011 Premature tenure as „Senior Scientist“ at Honda Research
Institute Europe GmbH

10/2006 – 2/2008 Four-year contract as „Senior Scientist“ at Honda Research
Institute Europe GmbH, Offenbach am Main, Germany

Assignments: Basic research in machine learning for intelligent
vehicles, implementation of prototypes and demonstrations,
communication to management and academic community,
supervision of students

PhD thesis

11/2002 – 04/2006 at the university of Bochum, institute for neural computation

Subject: „Neural learning methods for visual object recognition“

Degree: Dr. rer. nat (grade: „very good“)

Assignments: research, teaching, participation in third-party funded projects (Honda Research Institute Europe GmbH, Robert Bosch KG , DFG Sonderforschungsbereich 475)

Tertiary education

10/1996 – 01/2002 Studies in physics at Ludwig-Maximilians-Universität Munich

Diploma thesis: „Non-BPS states in string theory” (grade: 1,7)

Degree: diploma (grade: „very good“)

Alternate civil service (instead of army service)

8/1995 - 10/1996 at the municipal hospital Pfaffenhofen/Ilm

Secondary education

6/1995 at Schyren-Gymnasium Pfaffenhofen/Ilm, grade: 1,8

Skills

Computers Programming: C/C++, CUDA, Python, Matlab

Web programming: HTML, CSS, PHP

Operating systems: Windows, Linux

Real-time middleware: ROS

Scientific standard tools: LaTeX, svn, git, doxygen, bash, eclipse, gnuplot, make, cmake, ...

Libraries: OpenCV, Qt, numpy/scipy, matplotlib/pylab

Languages German, Czech: mother tongues

English, French: fluent

Spanish: advanced level

Japanese:basic level

Interests

Tennis, volleyball, bodybuilding, Go, playing the violin, real-time strategy games (Starcraft)

Publications

28
7
4
1
2
2
2
2
2
2
2
2
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
10
8
5
5
4
4
3
2
2
2
2
2
2
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
3
2
1
1
10
8
14
1
5
1

Publications

Marginal Replay vs Conditional Replay for Continual Learning

Timothée Lesort , Alexander Gepperth , Andrei Stoian , David Filliat
ICANN, 2019, Munich, Germany
Communication dans un congrès hal-02285835 v1
Image document

Learning to be attractive: probabilistic computation with dynamic attractor networks

Alexander Gepperth , Mathieu Lefort
Internal Conference on Development and LEarning (ICDL), 2016, Cergy-Pontoise, France
Communication dans un congrès hal-01418141 v1
Image document

Incremental Learning for Bootstrapping Object Classifier Models

Cem Karaoguz , Alexander Gepperth
IEEE International Conference On Intelligent Transportation Systems (ITSC), 2016, Seoul, South Korea
Communication dans un congrès hal-01418160 v1
Image document

Incremental learning algorithms and applications

Alexander Gepperth , Barbara Hammer
European Symposium on Artificial Neural Networks (ESANN), 2016, Bruges, Belgium
Communication dans un congrès hal-01418129 v1
Image document

Computational Advantages of Deep Prototype-Based Learning

Thomas Hecht , Alexander Gepperth
International Conference on Artificial Neural Networks (ICANN), 2016, Barcelona, Spain. pp.121 - 127, ⟨10.1007/978-3-319-44781-0_15⟩
Communication dans un congrès hal-01418135 v1
Image document

A Deep Learning Approach for Hand Posture Recognition from Depth Data

Thomas Kopinski , Fabian Sachara , Alexander Gepperth , Uwe Handmann
International Conference on Artificial Neural Networks (ICANN), 2016, Barcelona, Spain. pp.179 - 186, ⟨10.1007/978-3-319-44781-0_22⟩
Communication dans un congrès hal-01418137 v1
Image document

Towards incremental deep learning: multi-level change detection in a hierarchical recognition architecture

Thomas Hecht , Alexander Gepperth
European Symposium on Artificial Neural Networks (ESANN), 2016, Bruges, Belgium
Communication dans un congrès hal-01418132 v1
Image document

A light-weight real-time applicable hand gesture recognition system for automotive applications

Thomas Kopinski , Stéphane Magand , Alexander Gepperth , Uwe Handmann
IEEE International Symposium on Intelligent Vehicles (IV), Jun 2015, Seoul, South Korea. pp.336-342, ⟨10.1109/IVS.2015.7225708⟩
Communication dans un congrès hal-01251413 v1
Image document

Active learning of local predictable representations with artificial curiosity

Mathieu Lefort , Alexander Gepperth
International Conference on Development and Learning and Epigenetic Robotics (ICDL-Epirob), Aug 2015, Providence, United States
Communication dans un congrès hal-01205619 v1
Image document

Resource-efficient incremental learning in very high dimensions

Alexander Gepperth , Mathieu Lefort , Thomas Hecht , Ursula Körner
European Symposium on Artificial Neural Networks (ESANN), Apr 2015, Bruges, Belgium
Communication dans un congrès hal-01251015 v1
Image document

Learning of local predictable representations in partially learnable environments

Mathieu Lefort , Alexander Gepperth
The International Joint Conference on Neural Networks (IJCNN), Jul 2015, Killarney, Ireland
Communication dans un congrès hal-01205611 v1
Image document

Using self-organizing maps for regression: the importance of the output function

Thomas Hecht , Mathieu Lefort , Alexander Gepperth
European Symposium on Artificial Neural Networks (ESANN), Apr 2015, Bruges, Belgium
Communication dans un congrès hal-01251011 v1
Image document

A generative-discriminative learning model for noisy information fusion

Thomas Hecht , Alexander Gepperth
International Conference on Development and Learning (ICDL), Aug 2015, Providence, United States. ⟨10.1109/DEVLRN.2015.7346148⟩
Communication dans un congrès hal-01250967 v1
Image document

Biologically inspired incremental learning for high-dimensional spaces

Alexander Gepperth , Thomas Hecht , Mathieu Lefort , Ursula Körner
Joint IEEE International Conference Developmental Learning and Epigenetic Robotics (ICDL-EPIROB), Sep 2015, Providence, United States. ⟨10.1109/DEVLRN.2015.7346155⟩
Communication dans un congrès hal-01250961 v1
Image document

A simple technique for improving multi-class classification with neural networks

Thomas Kopinski , Alexander Gepperth , Uwe Handmann
European Symposium on artificial neural networks (ESANN), Jun 2015, Bruges, Belgium
Communication dans un congrès hal-01251009 v1
Image document

Context-based vector fields for multi-object tracking in application to road traffic

Egor Sattarov , Sergio Alberto Rodriguez Florez , Alexander Gepperth , Roger Reynaud
IEEE International Conference On Intelligent Transportation Systems (ITSC), Oct 2014, Qingdao, China. pp.1179 - 1185, ⟨10.1109/ITSC.2014.6957847⟩
Communication dans un congrès hal-01098701 v2
Image document

PROPRE: PROjection and PREdiction for multimodal correlations learning. An application to pedestrians visual data discrimination

Mathieu Lefort , Alexander Gepperth
IJCNN - International Joint Conference on Neural Networks, Jul 2014, Pékin, China
Communication dans un congrès hal-01061662 v1
Image document

A real-time applicable 3D gesture recognition system for automobile HMI

Thomas Kopinski , Stefan Geisler , Louis-Charles Caron , Alexander Gepperth , Uwe Handmann
IEEE International Conference On Intelligent Transportation Systems (ITSC), Oct 2014, Qingdao, China. pp.2616 - 2622, ⟨10.1109/ITSC.2014.6958109⟩
Communication dans un congrès hal-01098700 v1
Image document

Neural Network Based Data Fusion for Hand Pose Recognition with Multiple ToF Sensors

Thomas Kopinski , Alexander Gepperth , Stefan Geisler , Uwe Handmann
International Conference on Artificial Neural Networks (ICANN), Sep 2014, Hamburg, Germany. pp.233 - 240, ⟨10.1007/978-3-319-11179-7_30⟩
Communication dans un congrès hal-01098697 v1
Image document

Neural network based 2D/3D fusion for robotic object recognition

Louis-Charles Caron , Yang Song , David Filliat , Alexander Gepperth
European Symposium on artificial neural networks (ESANN), May 2014, Bruges, Belgium. pp.127 - 132
Communication dans un congrès hal-01012090 v1
Image document

Robust visual pedestrian detection by tight coupling to tracking

Alexander Gepperth , Egor Sattarov , Bernd Heisele , Sergio Alberto Rodriguez Florez
IEEE International Conference On Intelligent Transportation Systems (ITSC), Oct 2014, Qingdao, China. pp.1935 - 1940, ⟨10.1109/ITSC.2014.6957989⟩
Communication dans un congrès hal-01098703 v1
Image document

Time-of-Flight based multi-sensor fusion strategies for hand gesture recognition

Thomas Kopinski , Darius Malysiak , Alexander Gepperth , Uwe Handmann
IEEE International Symposium on Computational Intelligence and Informatics, Nov 2014, Budapest, Hungary
Communication dans un congrès hal-01098695 v1
Image document

Latency-based probabilistic information processing in a learning feedback hierarchy

Alexander Gepperth
International Joint Conference on Neural Networks (IJCNN), Jun 2014, Beijing, China. pp.3031 - 3037, ⟨10.1109/IJCNN.2014.6889919⟩
Communication dans un congrès hal-01098704 v1
Image document

A Multi-Modal System for Road Detection and Segmentation

Xiao Hu , Sergio Alberto Rodriguez Florez , Alexander Gepperth
IEEE Intelligent Vehicles Symposium, Jun 2014, Dearborn, Michigan, United States. pp.1365-1370
Communication dans un congrès hal-01023615 v1
Image document

Neural Network Fusion of Color, Depth and Location for Object Instance Recognition on a Mobile Robot

Louis-Charles Caron , David Filliat , Alexander Gepperth
Second Workshop on Assistive Computer Vision and Robotics (ACVR), in conjunction with European Conference on Computer Vision, Sep 2014, Zurich, Switzerland
Communication dans un congrès hal-01087392 v1
Image document

Discrimination of visual pedestrians data by combining projection and prediction learning

Mathieu Lefort , Alexander Gepperth
European Symposium on artificial neural networks (ESANN), Apr 2014, Bruges, Belgium
Communication dans un congrès hal-01061654 v1
Image document

Multimodal space representation driven by self-evaluation of predictability

Mathieu Lefort , Thomas Kopinski , Alexander Gepperth
Joint IEEE International Conference Developmental Learning and Epigenetic Robotics (ICDL-EPIROB), Oct 2014, Gênes, Italy
Communication dans un congrès hal-01061668 v1
Image document

Latency-Based Probabilistic Information Processing in Recurrent Neural Hierarchies

Alexander Gepperth , Mathieu Lefort
International Conference on Artificial Neural Networks (ICANN), Sep 2014, Hamburg, Germany. pp.715 - 722, ⟨10.1007/978-3-319-11179-7_90⟩
Communication dans un congrès hal-01098699 v1
Image document

Scene context is more than a Bayesian prior: Competitive vehicle detection with restricted detectors

Thomas Hecht , Mrinal Mohit , Egor Sattarov , Alexander Gepperth
IEEE International Symposium on Intelligent Vehicles(IV), May 2014, Detroit, United States. pp.1358 - 1364, ⟨10.1109/IVS.2014.6856542⟩
Communication dans un congrès hal-01098707 v1
Image document

A Comparison of Geometric and Energy-Based Point Cloud Semantic Segmentation Methods

Mathieu Dubois , Paola K. Rozo , Alexander Gepperth , Fabio A. González O. , David Filliat
6th European Conference on Mobile Robotics (ECMR), IEEE, Sep 2013, Barcelona, Spain. pp.88-93, ⟨10.1109/ECMR.2013.6698825⟩
Communication dans un congrès hal-00963863 v1
Image document

RGBD object recognition and visual texture classification for indoor semantic mapping

David Filliat , Emmanuel Battesti , Stéphane Bazeille , Guillaume Duceux , Alexander Gepperth et al.
Technologies for Practical Robot Applications (TePRA), 2012 IEEE International Conference on, Apr 2012, United States. pp.127 - 132, ⟨10.1109/TePRA.2012.6215666⟩
Communication dans un congrès hal-00755295 v1
Image document

Simultaneous concept formation driven by predictability

Alexander Gepperth , Louis-Charles Caron
International conference on development and learning, Nov 2012, San Diego, United States
Communication dans un congrès hal-00763671 v1
Image document

Co-training of context models for real-time object detection

Alexander Gepperth
IEEE Symposium on Intelligent Vehicles, Jun 2012, Madrid, Spain
Communication dans un congrès hal-00763676 v1
Image document

New learning paradigms for real-world environment perception

Alexander Gepperth
Machine Learning [cs.LG]. Université Pierre & Marie Curie, 2016
HDR tel-01418147 v1