Konstantin Willeke

Graduate Student

I am fascinated by the similarities between artificial neural networks and biological neural networks, and I am particularly interested in how machine learning algorithms and the brain are solving the complex task of vision. To gain insight into these matters, I am using deep neural networks to model the early visual cortex of monkeys and mice, to see in which cases these models work, and in which cases they do not. Using network dissection techniques and in silico experiments, my aim is to discover functional principles of artificial neural networks that are instructive for neuroscientific experiments, and that could lead to insights into the fundamentals of our cognitive system and its implementation. I am also passionate about open science, sharing of data and methods, and the movement of using AI to empower society.

Publications

Lab members are shown in this color.

2022

Luca Baroni, Mohammad Bashiri, Konstantin Friedrich Willeke, Ján Antolík, Fabian Sinz Learning Invariance Manifolds of Visual Sensory Neurons Neurips 2022 Workshop NeurReps workshop paper · system identification ·
Katrin Franke, Konstantin F. Willeke, Kayla Ponder, Mario Galdamez, Taliah Muhammad, Saumil Patel, Emmanouil Froudarakis, Jacob Reimer, Fabian H. Sinz, Andreas S. Tolias Behavioral state tunes mouse vision to ethological features through pupil dilation Nature journal paper · inception loops neuroscience · nature twitter biorXiv data code
Konstantin F. Willeke, Paul G. Fahey, Mohammad Bashiri, Laura Pede, Max F. Burg, Christoph Blessing, Santiago A. Cadena, Zhiwei Ding, Konstantin-Klemens Lurz, Kayla Ponder, Taliah Muhammad, Saumil S. Patel, Alexander S. Ecker, Andreas S. Tolias, Fabian H. Sinz The Sensorium competition on predicting large-scale mouse primary visual cortex activity arXiv preprint · system identification · arXiv challenge data
Santiago A. Cadena, Konstantin F. Willeke, Kelli Restivo, George Denfield, Fabian H. Sinz, Matthias Bethge, Andreas S. Tolias, Alexander S. Ecker Diverse task-driven modeling of macaque V4 reveals functional specialization towards semantic tasks bioRxiv preprint · normative models · bioRxiv
Jiakun Fu, Konstantin F. Willeke, Pawel A. Pierzchlewicz, Taliah Muhammad, George H. Denfield, Fabian H. Sinz, Andreas S. Tolias Hetereogenous orientation tuning across sub-regions of receptive fields of V1 neurons in mice Cell Press Sneak Preview preprint · inception loops neuroscience · cell press

2021

Shahd Safarani, Arne Nix, Konstantin Willeke, Santiago A. Cadena, Kelli Restivo, George Denfield, Andreas S. Tolias, Fabian H. Sinz Towards robust vision by multi-task learning on monkey visual cortex NeurIPS (accepted) conference paper · inductive bias transfer · arXiv github
Shahd Safarani, Arne Nix, Konstantin Willeke, Santiago A. Cadena, Kelli Restivo, George Denfield, Andreas S. Tolias, Fabian H. Sinz Towards robust vision by multi-task learning on monkey visual cortex ICLR 2021 Workshop: How Can Findings About The Brain Improve AI Systems? workshop paper · inductive bias transfer · workshop youtube pdf
Konstantin-Klemens Lurz, Mohammad Bashiri, Konstantin Friedrich Willeke, Akshay Kumar Jagadish, Eric Wang, Edgar Y Walker, Santiago Cadena, Taliah Muhammad, Eric Cobos, Andreas Tolias, Alexander Ecker, Fabian Sinz Generalization in data-driven models of primary visual cortex ICLR (spotlight) conference paper · system identification · openreview bioRxiv twitter data code youtube