GEMESYS
Daniel Krüger is a Co-Founder and CTO at GEMESYS, where the focus is on IC Design for brain-inspired AI hardware since August 2023. Previously, Krüger served as Lead IC Design Engineer at Axoft, specializing in implantable neural interfaces from April 2022 to July 2023. Daniel conducted research as a Fellow and PhD candidate at Harvard University from January 2020 to June 2023, working on CMOS transceivers for nuclear magnetic resonance and magnetic resonance imaging in the Donhee Ham Lab. Earlier experience includes a role as a Working Student at umlaut company in electronics and hardware development from May 2014 to December 2018, and as a Student Assistant during an internship at the University of Stuttgart's Institute of Industrial Automation and Software Engineering. Daniel Krüger holds a PhD in Engineering Sciences and a Master's and Bachelor's in Electrical Engineering, all from the University of Stuttgart.
This person is not in any teams
GEMESYS
Current hardware for artificial intelligence is inefficient. For today's supercomputer center, it takes a long time, huge datasets and the energy of a whole power plant to train a high-end AI model, resulting in high costs and unsustainability. The problem is rooted in the fundamental architecture of today’s digital hardware itself, since it has nothing in common with the way the human brain works. GEMESYS Technologies offers an analog chip design based on the same information-processing mechanisms as the human brain. This enables AI hardware vendors to distribute a novel chip, that trains neural networks 20,000 times more energy-efficient than current technology. It not only significantly reduces the cost, time and amount of data required to train a neural network, but also increases overall quality as well as performance. Its small size and high energy efficiency allows it to be embedded in nearly every device, enabling decentralized on the edge training, data processing and decision making.