Building artificial neural networks inspired by the brain
The requirements of real biological neural networks are modest compared to the complex deep neural networks used in machine learning, which come with substantial memory and energy demands. The Zenke group has developed a new method in machine learning called Neural Tangent Transfer to make a sparse neural network which performs almost as well as a densely connected deep neural network on various learning tasks, but at a heavily reduced computing cost.
About the FMI
The Friedrich Miescher Institute for Biomedical Research (FMI), based in Basel, Switzerland, is a world-class biomedical research institute, affiliated with the University of Basel and the Novartis Institutes for Biomedical Research.
Learn more about our open position
Apply to our PhD and MD-PhD Programs
Group leader video: Marc Bühler
Upcoming Seminars & Events
Due to the current coronavirus situation, all live seminars and events at the FMI have been cancelled or postponed.
We will feature content in this section once we will have public events again.
Opposing Influence of Top-down and Bottom-up Input on Excitatory Layer 2/3 Neurons in Mouse Primary Visual Cortex.
DNA Damage-Induced Nucleosome Depletion Enhances Homology Search Independently of Local Break Movement.