Optics-informed Neural Networks: Bridging Deep Learning with Photonic Accelerators

Miltiadis Moralis-Pegios, Apostolos Tsakyridis, Christos Pappas, Theodoros Moschos, George Giamougiannis, Stefanos Kovaios, Ioannis Roumpos, Manos Kirtas, Nikos Passalis, Anastasios Tefas, Nikos Pleros

Abstract: We discuss our work in optics informed photonic neural networks, an architectural framework bridging the idiosyncrasy of integrated photonic architectures with a set of Deep Learning algorithms, towards harnessing the full potential of light-based accelerators.