Optical machine learning with incoherent light and a single-pixel detector
This is an incremental improvement for optical computing systems, enabling more practical deployment in machine learning tasks.
The paper tackles the limitations of optical diffractive neural networks, which require coherent light and high precision, by proposing an optical machine learning framework based on single-pixel imaging that works under incoherent lighting with lower complexity and programmability.
An optical diffractive neural network (DNN) can be implemented with a cascaded phase mask architecture. Like an optical computer, the system can perform machine learning tasks such as number digit recognition in an all-optical manner. However, the system can only work under coherent light illumination and the precision requirement in practical experiments is quite high. This paper proposes an optical machine learning framework based on single-pixel imaging (MLSPI). The MLSPI system can perform the same linear pattern recognition task as DNN. Furthermore, it can work under incoherent lighting conditions, has lower experimental complexity and can be easily programmable.