Eurekalert July 19, 2018 There is interest in using integrated optics as a hardware platform for implementing artificial neural networks. However, currently on the integrated photonics platform there is no efficient protocol for the training of these networks. Researchers at Stanford University have developed a method that enables highly efficient, in situ training of a photonic neural network by using adjoint variable methods to derive the photonic analogue of the backpropagation algorithm. As demonstration they trained a numerically simulated photonic artificial neural network. The method may be of broad interest to experimental sensitivity analysis of photonic systems and optimization of […]