Matthias

Matthias Bethge

Publications, Email, Homepage, Phone: +49 7071 29 70862
Group Leader
My research goal is to understand how the brain makes sense of its high-dimensional sensory input. In particular, I seek to understand the formation of distributed neural representations in the visual system by studying deep neural networks, natural image statistics, unsupervised learning, and neural population coding, and by developing new data-analysis tools.
Heike

Heike König

Email, Phone: +49 7071 29 70865
Assistant
Judith

Judith Lam

Email, Homepage, Phone: +49 7071 29 70866
Coordinator SFB1233 & BCCN Tübingen
At the Bernstein Center Tübingen, scientists from various disciplines, including theoretical and experimental neurobiology, machine learning, and medicine, collaborate in order to analyze the basis of inference processes in the brain. In particular, a main research goal is to understand the coordinated interaction of neurons during information processing.
Monika

Monika Lam

Email, Phone: +49 7071 29 70867
Coordinator Tübingen AI Center & ELLIS
Executive coordinator of the Tübingen AI Center (Competence Center for Machine Learning) and the European Laboratory for Learning and Intelligent Systems (ELLIS)
Caroline

Caroline Schmidt

Email, Phone: +49 7071 29 70880
Outreach Coordinator
Coordinator for outreach activities including the National Competiton for Artificial Intelligence (Bundeswettbewerb Künstliche Intelligenz) and the IT training activity at primary schools (It4Kids).
Alexander

Alexander Ecker

Publications, Email, Phone: +49 7071 29 70864
Project Leader
I want understand how neural systems perform visual perception. At the interface of computer vision and neuroscience, I try to understand both how the human visual system works and how to teach computers to make sense of images. I use an interdisciplinary approach that combines methods from machine learning and computer vision with behavioral studies and neuronal population recordings in the brain. My work is driven by the idea that we can advance artificial intelligence by understanding how biological systems implement intelligent behavior.
Wieland

Wieland Brendel

Publications, Email, Phone: +49 7071 29 70 863
Postdoc
My research goal is to close the gap between the visual information processing in humans and machines. One of the most striking differences is the susceptibility of Deep Neural Networks (DNNs) to almost imperceptible perturbations of their inputs. Getting machines closer to humans will require fundamentally new concepts to learn causal models of the world. My work aims to quantify the robustness of DNNs, to identify the causes for their susceptibility and to devise solutions by drawing inspiration from Neuroscience and Computer Vision.
Alexander

Alexander Mathis

Publications, Email, Homepage
Postdoc
I am a Marie Curie fellow in the lab of Professor Venkatesh Murthy at the Department of Molecular and Cellular Biology at Harvard University and with Professor Matthias Bethge at the Bernstein Center for Computational Neuroscience at the University of Tuebingen. My main research interests comprise active sensing, odor-guided navigation and optimal coding.
Judy

Judy Borowski

Publications, Email, Phone: +49 7071 29 70582
Graduate Student
I aim to improve understanding visual perception by connecting state-of-the-art object recognition algorithms and the human visual system. Currently, I focus on how to adequately compare these two fundamentally different systems and on how much more understandable humans find convolutional neural networks thanks to interpretability methods. Besides research, I am enthusiastic about outreach and teaching programming (for example with the project IT4Kids).
Alexander

Alexander Böttcher

Publications, Email, Phone: +49 7071 29 70881
Graduate Student
My aim is to understand how the activity of sensory neurons leads to decisions taken by the brain. In particular, I am interested in neural population coding of the primary somatosensory cortex.
Santiago

Santiago Cadena

Publications, Email, Phone: +49 7071 29 70876
Graduate Student
I study visual processing in the brain by building predictive models of population responses from the macaque and rodent brains to image and video sequences. I leverage on advances in machine learning and computer vision to both improve predictive power and to gain insights into the nonlinear computations of visual neurons. My goal is to be able to use these insights to enhance current computer vision methods.
Christina

Christina Funke

Publications, Email, Phone: +49 7071 29 70874
Graduate Student
Robert

Robert Geirhos

Publications, Email, Phone: +49 7071 29 70582
Graduate Student
Are human and machine vision relying on similar strategies for visual processing? I use psychophysical methods to better understand machine vision, and convolutional neural networks to model aspects of human visual processing. A current focus of my work is robustness: What can machine vision learn from the incredibly general robustness of the human visual system towards distortions of any kind?
Max

Max Günthner

Publications, Email, Phone: +49 7071 29 70874
Graduate Student
David

David Klindt

Publications, Email, Phone: +49 7071 29 70876
Graduate Student
My research focuses on robust biological vision. Neuroscience has provided incredible inductive biases that led to breakthroughs in deep learning and computer vision. For instance, by suggesting hierarchical retinotopic visual processing in the brain that inspired the development of modern CNNs. Now computer vision has caught up and even excelled human performance in many different visual tasks. I am trying to deploy the lessons learned in deep learning and bring them back to visual neuroscience, e.g. with the idea of feature maps in the retina that share computations across types of neurons. Simultaneously, the computations we are still discovering in biological vision need to be explored further, e.g. to see how they can make the current generation of CNNs more robust to adversarial perturbations and more human-like in their visual understanding of the world.
Matthias

Matthias Kümmerer

Publications, Email, Phone: +49 7071 29 70585
Graduate Student
Learning what properties of an image are associated with human gaze placement is important both for understanding how biological systems explore the environment and for computer vision applications. Recent advances in deep learning for the first time enable us to explain a significant portion of the information expressed in the spatial fixation structure. My interest is twofold: I want to create better models for predicting human fixations in different tasks and on the other hand make use of these models to increase our understanding of how humans perform this task from a neuroscientific and psychophysical standpoint.
Claudio

Claudio Michaelis

Publications, Email, Phone: +49 7071 29 70877
Graduate Student
Humans do not only excel at acquiring novel concepts from a single demonstration but can also readily identify or reproduce them. When shown a new object humans have no problem pointing at similar objects or drawing their outlines. My goal is to bring similar capabilities to computer vision systems.
Marlene

Marlene Prautzsch

Publications, Email
Graduate Student
Jonas

Jonas Rauber

Publications, Email, Homepage, Phone: +49 7071 29 70875
Graduate Student
I want to build more intelligent machines that improve our lives, and doing so by taking inspiration from humans: learning with little supervision, being robust to perturbations, generalizing across tasks, combining modalities, or utilizing hierarchical relationships. In particular, my current research focuses on understanding and improving the robustness of deep neural networks to adversarial perturbations.
Evgenia

Evgenia Rusak

Publications, Email, Phone: +49 7071 29 70873
Graduate Student
To enable a future where autonomous cars can replace human drivers, we have to ensure that the autonomous agents make the right decisions at all times. In particular, bad weather scenarios currently pose a big problem for important tasks such as object detection and scene understanding. In my PhD, I work on improving the robustness of Deep Neural Nets to natural distortions such as rain or snow.
Lukas

Lukas Schott

Publications, Email, Homepage, Phone: +49 7071 29 70875
Graduate Student
I aim to explore and narrow the gap between human and machine perception. My current focus is on adversarial examples: minimal and humanly almost imperceptible image perturbations which derail neural network predictions. This can also be viewed as a worst case of generalization. One goal is to overcome this problem by more fundamentally adapting the information processing in neural networks using feedback connections to perform an analysis by synthesis. This work involves probabilistic generative models and Bayesian inference.
Yash

Yash Sharma

Publications, Email, Homepage, Phone: +49 7071 29 70878
Graduate Student
I aim to reduce the reliance upon data and compute by enabling agents to capture the causal factors of complex input through the induction of stronger priors.
Matthias

Matthias Tangemann

Publications, Email, Phone: +49 7071 29 70585
Graduate Student
I am interested in temporal aspects of vision and unsupervised learning. The capabilities of the human visual system originate from a dynamic environment and are largely learned without supervision. I would like to explore how temporal information affects computer vision tasks as gaze prediction, segmentation or scene understanding and how it can be used to learn useful representations of our world without supervision.
Ivan

Ivan Ustyuzhaninov

Publications, Email, Phone: +49 7071 29 70873
Graduate Student
Marissa

Marissa Weis

Publications, Email, Phone: +49 7071 29 70877
Graduate Student
Benjamin

Benjamin Mitzkus

Publications, Email
Master Student
Judith

Judith Schepers

Publications, Email, Phone: +49 7071 29 70585
Master Student
Steffen

Steffen Schneider

Publications, Email, Homepage
Master Student
My goal is to build machine learning models capable of approaching the performance of biological brains in terms of data-efficiency and robustness to perturbations and changes in their environment. Drawing inspiration from adaptation behavior of biological systems, I study methods for domain adaptation, transfer learning and semi-supervised learning.
Roland

Roland Zimmermann

Publications, Email, Homepage, Phone: +49 7071 29 70875
Master Student
University of Tuebingen BCCN CIN MPI