We conduct theoretical research on how neural networks learn and compute. To that end, 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 »
WordPress RSS Feed by Theme Mason