Identifying topology of leaky photonic lattices with machine learning.

We show how machine learning techniques can be applied for the classification of topological phases in finite leaky photonic lattices using limited measurement data. We propose an approach based solely on a single real-space bulk intensity image, thus exempt from complicated phase retrieval procedures. In particular, we design a fully connected neural network that accurately determines topological properties from the output intensity distribution in dimerized waveguide arrays with leaky channels, after propagation of a spatially localized initial excitation at a finite distance, in a setting that closely emulates realistic experimental conditions.