BAYESBRAIN - THE WORLD'S FIRST HYBRID NEURO-SILICON AI COMPUTER
Computation in biological brain tissue consumes about a million times less power than silicon-based AI systems. Motivated by this fact, this project aims to develop the world’s first hybrid neuro-silicon AI computer, introducing a fundamentally new paradigm of AI computing. We will combine an in-silico Bayesian control agent with neural tissue hosted by a microfluidic Brain-on-Chip (BoC) that together form a hybrid learning system capable of solving real-world AI problems.
Regina Luttge studied Applied Sciences in Germany and worked as an engineering researcher at Institut für Mikrotechnik in Mainz for nearly five years prior to starting her PhD studies in Microsystems Technologies at Imperial College, London, in 1999. In 2003 she received her PhD from the University of London on the development of fabrication technology for micro-optical scanners. Switching her research interest to microfluidics applications, Luttge went on to work at the University of Twente MESA+ Institute for Nanotechnology. Initially as a senior scientist and later as an Assistant Professor. She was appointed Associate Professor in the TU/e Microsystems Group in 2013. Regina Luttge is Chair of Neuro-Nanoscale Engineering at Eindhoven University of Technology. Her research line investigates and develops microsystems for medicine and biology with integrated bio-inspired functionality mediated by shrinking structural dimensions and controlling material properties at the nanoscale applying emerging and established micro-nanofabrication methods.
BERT DE VRIES
Bert de Vries received M.Sc. (1986) and Ph.D. (1991) degrees in Electrical Engineering from Eindhoven University of Technology (TU/e) and the University of Florida, respectively. From 1992 to 1999, he worked as a research scientist at Sarnoff Research Center in Princeton (NJ, USA). Since 1999, he has been employed in the hearing aids industry, both in engineering and managerial positions. De Vries was appointed part-time professor in the Signal Processing Systems Group at TU/e in 2012. His research focuses on the development of intelligent autonomous agents that learn from in-situ interactions with their environment. And on using these agents to automate the development of novel signal processing algorithms, see biaslab.org. Our research draws inspiration from diverse fields including computational neuroscience, Bayesian machine learning and signal processing systems. A current major application area concerns personalization of medical signal processing systems such as hearing aid algorithms. In the past, De Vries contributed to research projects over a wide range of signal and image processing topics, such as word spotting, financial market prediction and breast cancer detection from mammograms.
Go back to RESEARCH TRACK