We conduct theoretical research on how neural networks learn and compute. We work at the interface of computational neuroscience and machine learning. Our group is based at the FMI in Basel, Switzerland.
- Paper: Surrogate Gradient Learning in Spiking Neural Networks“Bringing the Power of Gradient-based optimization to spiking neural networks” We are happy to announce that our tutorial paper on Surrogate Gradient Learning in spiking neural networks now appeared in the IEEE Signal Processing Magazine. Great team effort with Emre Neftci and Hesham Mostafa. Unfortunately, the paper is behind a… Read more »
- Perspective: A deep learning framework for neuroscienceOur perspective paper on how systems neuroscience can benefit from deep learning was published today. In work led by Blake Richards, Tim Lillicrap, and Konrad Kording, we argue that focusing on the three core elements used to design deep learning systems — network architecture, objective functions, and learning rules — offers… Read more »
- Preprint: The Heidelberg spiking datasets for the systematic evaluation of spiking neural networksA range of exciting developments around surrogate gradient methods has put researchers in the position to build sophisticated functional spiking neural networks that compute specific functions. A major hurdle to further accelerate this line of research is the lack of free spike-based benchmark datasets that are not saturated by existing… Read more »
WordPress RSS Feed by Theme Mason