Gradient Descent in Materio

no code implementations • 15 May 2021 • Marcus N. Boon, Hans-Christian Ruiz Euler, Tao Chen, Bram van de Ven, Unai Alegre Ibarra, Peter A. Bobbert, Wilfred G. van der Wiel

Here, we demonstrate an efficient and accurate homodyne gradient extraction method for performing gradient descent on the loss function directly in the material system.

Dopant Network Processing Units: Towards Efficient Neural-network Emulators with High-capacity Nanoelectronic Nodes

1 code implementation • 24 Jul 2020 • Hans-Christian Ruiz-Euler, Unai Alegre-Ibarra, Bram van de Ven, Hajo Broersma, Peter A. Bobbert, Wilfred G. van der Wiel

By implementing and testing a small multi-DNPU classifier in hardware, we show that feed-forward DNPU networks improve the performance of a single DNPU from 77% to 94% test accuracy on a binary classification task with concentric classes on a plane.

Binary Classification Efficient Neural Network