Novel Devices

The Physical Computation Laboratory investigates methods for exploiting knowledge of the physical properties of materials to create more efficient computation structures (e.g., AI hardware accelerators) which process data from the physical world.

Bridging the Band Gap: What Device Physicists Need to Know About Machine Learning

Nathaniel Tye, Stephan Hofmann, Phillip Stanley-Marbell, ArXiv preprint.      
Members Public

Bridging the Band Gap: What Device Physicists Need to Know About Machine Learning
Research Theme: Graphene FETs for Physics-Enhanced Machine Learning (Grappa)
Members Public

Research Theme: Graphene FETs for Physics-Enhanced Machine Learning (Grappa)
A System for Generating Non-Uniform Random Variates Using Graphene Field-Effect Transistors

N. J. Tye, J. T. Meech, B. A. Bilgin, and P. Stanley-Marbell, 31st IEEE International Conference on Application-specific Systems, Architectures and Processors, July 2020.      
Members Public

A System for Generating Non-Uniform Random Variates Using Graphene Field-Effect Transistors
How device properties influence energy-delay metrics and the energy-efficiency of parallel computations

Phillip Stanley-Marbell, HotPower '15: Proceedings of the Workshop on Power-Aware Computing and Systems October 2015.      
Members Public

How device properties influence energy-delay metrics and the energy-efficiency of parallel computations