Computer Scientist / AI Researcher
My name is Manuel Traub. I am a doctoral student in the Cognitive Modeling group at Eberhard Karls University of Tuebingen and a scholar of the International Max Planck Research School for Intelligent Systems.
During my masters, I specialized in AI reserach. Especially the field of Spiking Neural Networks (SNN) fascinates me.
The first experience with SNNs came from a small internship, and later from a research project. The greatest learning opportunity so far was my masters thesis, where I controlled the movement of a many-joint robotic arm using an SNN. Here I investigated different biologically pausible training and inference algorithms which I first tested on a simulation and later on a real robot arm that I designed and built by myself, using a 3D-printer.
I am a passionate programmer and wrote almost all of the SNN related code during my masters by myself. The whole framework, which I am still continuing to develop, is written purely in C++ with CUDA extension to run computationally expensive calculations on my grafic cards.
My current research involves the training of Izhikevich Neurons which model biological neurons more accurately than the widespread used Leaky Integrate and Fire model.
My other interests include 3D-printing and robotics. In my free time, I am a passionate strength athlete and outdoor enthusiast.
M. Traub, M. V. Butz, R. Legenstein, and S. Otte. Dynamic action inference with recurrent spiking neural networks International Conference on Artificial Neural Networks, 2021
M. Traub, R. Legenstein, and S. Otte. Many-Joint Robot Arm Control with Recurrent Spiking Neural Networks International Conference on Intelligent Robots and Systems, 2021
M. Traub, M. V. Butz, R. H. Baayen, and S. Otte. Learning precise spike timings with eligibility traces. International Conference on Artificial Neural Networks. Springer, Cham, 2020.
M. Traub. Biologically inspired action inference with recurrent spiking forward models. Master’s thesis, Eberhard Karls Universität Tübingen, 2019.
M. Traub, J. Stegmaier. Towards Automatic Embryo Staging in 3D+ T Microscopy Images using Convolutional Neural Networks and PointNets. International Workshop on Simulation and Synthesis in Medical Imaging. Springer, Cham, 2020.
B. Schott, M. Traub, C. Schlagenhauf, M. Takamiya, T. Antritter, A. Bartschat, K. Löffler, D. Blessing, J. C. Otte, A. Y. Kobitski, et al. Embryominer: A new framework for interactive knowledge discovery in large-scale cell tracking data of developing embryos. PLoS computational biology, 14(4):e1006128, 2018.
M. Traub. Design, implementation and evaluation of a visual interface to guide the knowledge discovery process within large biological datasets. Bachelor thesis, Karlsruher Institut für Technologie, 2016.
J. Stegmaier, B. Schott, E. Hübner, M. Traub, M. Shahid, M. Takamiya, A. Kobitski, V. Hartmann, R. Stotzka, J. van Wezel, et al. Automation strategies for large-scale 3d image analysis. at-Automatisierungstechnik, 64(7):555–566, 2016.