April 20, 2024 | Log in
 
 

Dr. rer. nat. Michael Teichmann

 


Chemnitz University of Technology
Department of Computer Science
Professorship Artificial Intelligence
Straße der Nationen 62, Room B309c, 09111 Chemnitz

Phone +49 371 531-39189
Fax     +49 371 531-39189
E-Mail: michael.teichmann (at) informatik.tu-chemnitz.de

 

PhD Project

“Modeling Vision” in the subfield Emotions of the research training group
Supervised by Prof. Dr. Fred Hamker (Artificial Intelligence)
Research partner: Benny Liebold, M.A.

 

Research Objectives

Modeling intelligent systems.

  • Adaptive systems and learning mechanisms
  • Visual perception
  • Influence of emotions on perception

 

Curriculum Vitae

09/2018 Dissertation in Artificial Intelligence, Dr. rer. nat.
since 04/2015 Research associate at Professorship of Artificial Intelligence
04/2012 – 03/2015 PhD student at research training group “Crossworlds”
10/2010 – 03/2012 Research associate at Professorship of Artificial Intelligence
10/2004 – 09/2010 Major in Computer Science, Minor in Artificial Intelligence and Operation Research
University award for the best thesis in computer science
Thesis: “Learning invariance in object recognition inspired by observations in the primary visual cortex of primates“

 

Publications

Peer-reviewed journal articles

  • Kermani Kolankeh, A., Teichmann, M., Hamker, F. (2015). Competition improves robustness against loss of information. Frontiers in Computational Neuroscience, 9:35. (link)
  • Liebold, B., Richter, R., Teichmann, M., Hamker, F., Ohler, P. (2015). Human Capacities for Emotion Recognition and their Implications for Computer Vision. i-com, 14(2), 126-137. ISSN 2196-6826 (link)
  • Teichmann, M., Wiltschut, J., Hamker, F. (2012). Learning invariance from natural images inspired by observations in the primary visual cortex. Neural Computation, 24(5), 1271–96. (link)

Peer-reviewed articles

  • Larisch, R., Teichmann, M., Hamker, F. (2018) A Neural Spiking Approach Compared to Deep Feedforward Networks on Stepwise Pixel Erasement. In: Kurková V., Manolopoulos Y., Hammer B., Iliadis L., Maglogiannis I. (eds) Artificial Neural Networks and Machine Learning – ICANN 2018. ICANN 2018. Lecture Notes in Computer Science, vol 11139. Springer, Cham (link)
  • Teichmann, M., Hamker, F. (2015). Intrinsic plasticity: A simple mechanism to stabilize Hebbian learning in multilayer neural networks. In T. Villmann, & F.-M. Schleif (Eds.), Proceedings of the Workshop New Challenges in Neural Computation – NC² 2015, Machine Learning Reports 03/2015 (pp. 103-111). ISSN 1865-3960 (link)
  • Kermani Kolankeh, A., Teichmann, M., Hamker, F. (2014). Role of competition in robustness under loss of information in feature detectors. In T. Villmann, & F.-M. Schleif (Eds.), Proceedings of the Workshop New Challenges in Neural Computation – NC² 2014, Machine Learning Reports 02/2014 (pp. 16-19). ISSN 1865-3960 (link)
  • Teichmann, M. (2012). Design von Objekterkennungssystemen basierend auf dem visuellen System des Menschen. Chemnitzer Informatik-Berichte, 12(1), 91-7. ISSN 0947-5125 (link/link)

Peer-reviewed posters and abstracts

  • Teichmann. M., Hamker. F. (2018). Specific connectivity in a model of V1 and V2 combining synaptic, intrinsic, and structural plasticity. Bernstein Conference 2018. (link)
  • Larisch, R., Gönner, L., Teichmann, M., Hamker, F. (2018). Voltage-based STDP and inhibitory plasticity cooperate to improve stimulus coding in a model of V1 simple-cells. Bernstein Conference 2018. (link)
  • Teichmann, M., Hamker, F. (2017). Learning Stable Recurrent Excitation in Simulated Biological Neural Networks. In A. Lintas et al. (Eds.), ICANN 2017, Part I, LNCS 10613, pp. 449-450. (link)
  • Larisch ,R., Gönner, L., Teichmann, M., Hamker, F. (2016). Combination of voltage­-based STDP with symmetric iSTDP to learn V1 simple­-cells. Conference Abstract: Bernstein Conference 2016. (link)
  • Teichmann, M., Hamker, F. (2016). Biologically plausible Hebbian learning in deep neural networks: being more close to the nature than CNNs. Journal of Vision 2016,16(12):178. (link)
  • Schuster, J., Teichmann, M., Hamker, F. (2015). A computational model of the perisaccadic updating of spatial attention. Bernstein Conference 2015, Heidelberg, Germany. (link)
  • Teichmann, M., Schuster, J., Hamker, F. (2015). A computational model of the perisaccadic updating of spatial attention. Journal of Vision 2015,15(12):69. (link)
  • Teichmann, M., and Hamker, F. (2013). A Single Learning Rule can Account for the Development of Simple and Complex Cells. 36th European Conference on Visual Perception, Bremen, Germany, 147. ISSN 0301-0066 (print) 1468-4233 (electronic) (link/link)
  • Teichmann, M., Shinn, M., Hamker, F. (2013). What are the Benefits of Structural Plasticity in a Model of the Primary Visual Cortex? Bernstein Conference 2013, Tübingen, Germany. (link)
  • Kermani Kolankeh, A., Teichmann, M., Hamker, F. (2013). Unsupervised neural learning improves image classification under occlussion. Bernstein Conference 2013, Tübingen, Germany. (link)
  • Teichmann, M., and Hamker, F. (2013). Modeling Vision using homeostatic Hebbian Plasticity in a recurrent Network. OCCAM2013, Osnabrück Computational Cognition Alliance Meeting, Osnabrück, Germany. (homepage)
  • Teichmann, M., and Hamker, F. (2012). Learning invariance in visual perception. Front. Comput. Neurosci. Conference Abstract: Bernstein Conference 2012. (link)
  • Teichmann, M., Wiltschut, J., Hamker, F. (2011). Learning invariance from natural images inspired by observations in the primary visual cortex. Workshop on Learning and Plasticity, CIRM, Marseille, France. (homepage)
  • Teichmann, M., Wiltschut, J., Hamker, F. (2010). Learning invariance from natural images inspired by observations in the primary visual cortex. International Workshop: Neuro-Cognitive Mechanisms of Conscious and Unconscious Visual Perception, Hanse-Wissenschaftskolleg (HWK), Delmenhorst, Germany. (homepage)

Talks (peer-reviewed)

  • Teichmann, M., and Hamker, F. (2016). Spatial Synaptic Growth and Removal for Learning Individual Receptive Field Structures. MODVIS 2016 Computational and Mathematical Models in Vision, St. Pete Beach, Florida, USA. (link)
  • Teichmann, M., and Hamker, F. (2015). A recurrent multilayer model with Hebbian learning and intrinsic plasticity. MODVIS 2015 Computational and Mathematical Models in Vision, St. Pete Beach, Florida, USA. (link)

Others

  • Teichmann, M. (2018). A plastic multilayer network of the early visual system
    inspired by the neocortical circuit. Dissertation. Universitätsverlag der Technischen Universität Chemnitz, Chemnitz. ISBN978-3-96100-065-4 (link)
  • Bischof, A., Obländer, V., Heidt, M., Kanellopoulos, K., Küszter, V., Liebold, B., Martin, K.-U., Pietschmann, D., Storz, M., Tallig, A., Teichmann, M., Wuttke, M. (2013). Interdisziplinäre Impulse für den Begriff “Interaktion”. In Hobohm, H.-C. (Hrsg.), Informationswissenschaft zwischen virtueller Infrastruktur und materiellen Lebenswelten. Tagungsband des 13. Internationalen Symposiums für Informationswissenschaft (ISI 2013), Potsdam, 19.-22.03.2013. Glücksstadt: Hülsbusch, 448-453. ISSN 0938-8710 (link)