About me

I am a PhD student in the lab of Friedemann Zenke at the Friedrich Miescher Institute, where I work in computational neuroscience and focus on understanding spiking neural networks.

I completed my master’s degree in biomedical engineering at ETH Zürich. During my master’s I worked on a biologically plausible implementation of an autoencoder in spiking neural networks in Giacomo Indiveri’s lab at INI and I wrote my master’s thesis in Benjamin Grewe’s lab on minimum norm optimization.

Before that, I received a bachelor’s degree in electrical engineering and information technology from ETH Zürich. During my final year, I was a member of the Cardex focus project team. We developed a transcatheter mitral valve repair simulator as a novel training technology for cardiovascular interventions.

News

• 2024-10-26: Tengjun Liu, Julian Rossbroich and I won first prize at the IEEE BiOCAS 2024 neural decoding challenge for our work on efficient cortical spike train decoding with recurrent spiking neural networks achieving the best trade-off between decoding accuracy and computational cost.
• 2024-10-01: Poster at Bernstein Conference 2024 - Efficient cortical spike train decoding for brain-machine interface implants with recurrent spiking neural networks (joint work with Tengjun Liu and Julian Rosbroich)
• 2024-09-20: Tengjun Liu, Julian Rossbroich and I won the Ruth Chiquet Prize for our work on efficient cortical spike train decoding with spiking neural networks. The Ruth Chiquet prize is awarded to honor research ingenuity.
• 2024-09-12: Talk at the Control Theory Group of Prof. Mustafa Khammash, ETH (D-BSSE) - Training spiking neural networks: Relating surrogate gradients, probabilistic models, and stochastic automatic differentiation
• 2024-09-03: Our new preprint Decoding finger velocity from cortical spike trains with recurrent spiking neural networks as a submission to the IEEE BiOCAS 2024 Grand Challenge on Neural Decoding is available on arXiv (joint work with Tengjun Liu and Julian Rossbroich)
• 2024-08-30: Talk at Giessbach@Rasses 2024 meeting - Building plausible spiking neural network models in-silico
• 2024-04-24: Our new preprint Elucidating the Theoretical Underpinnings of Surrogate Gradient Learning in Spiking Neural Networks is available on arXiv
• 2023-11-07: Flash talk and Poster at SNUFA 2023 - Comparing surrogate gradients and likelihood-based training for spiking neural networks
• 2023-09-27: Poster at Bernstein Conference 2023 - A comparative analysis of spiking network training with surrogate gradients and likelihood-based approaches
• 2023-06-09: Poster at Early-Career Researchers Symposium 2023 in Lugano
• 2023-02-01: Talk at Swiss Computational Neuroscience Retreat - Insights into spiking network training: Influences of initialization and neuronal stochasticity
• 2022-12-31: Our paper Fluctuation-driven initialization for spiking neural network training was selected as one of the Highlights of 2022 in the IOP Neuromorphic Computing and Engineering journal
• 2022-12-08: Our paper Fluctuation-driven initialization for spiking neural network training was published in Neuromorphic Computing and Engineering (joint work with Julian Rossbroich)
• 2022-09-14: Poster at Bernstein Conference 2022, joint work with Julian Rossbroich - Fluctuation-driven initialization for spiking neural network training
• 2021-11-03: Talk at SNUFA 2021 - Optimal initialization strategies for deep spiking neural networks