Teaching a neural network with non-tunable exciton-polariton nodes

Andrzej Opala, Riccardo Panico, Vincenzo Ardizzone, Barbara Pietka, Jacek Szczytko, Daniele Sanvitto, Michał Matuszewski, Dario Ballarini

In contrast to software simulations of neural networks, hardware or neuromorphic implementations have often limited or no tunability. While such networks promise great improvements in terms of speed and energy efficiency, their performance is limited by the difficulty to apply efficient teaching. We propose a system of non-tunable exciton-polariton nodes and an efficient teaching method that relies on the precise measurement of the nonlinear node response and the subsequent use of the backpropagation algorithm. We demonstrate experimentally that the classification accuracy in the MNIST handwritten digit benchmark is greatly improved compared to the case where backpropagation is not used.

Knowledge Graph

arrow_drop_up

Comments

Sign up or login to leave a comment