Misaligned orientations of 4f optical neural network for image classification accuracy on various datasets
This addresses the practical issue of device misalignment in optical neural networks for researchers and engineers, but it is incremental as it focuses on analyzing an existing problem rather than introducing a new solution.
The study investigated how misalignment in optical 4f systems affects the accuracy of optical neural networks for image classification, finding that performance degrades significantly with increased positioning error, but can be preserved with errors up to 200 microns in specific directions on MNIST and Quickdraw16 datasets.
In recent years, the optical 4f system has drawn much attention in building high-speed and ultra-low-power optical neural networks (ONNs). Most optical systems suffer from the misalignment of the optical devices during installment. The performance of ONN based on the optical 4f system (4f-ONN) is considered sensitive to the misalignment in the optical path introduced. In order to comprehensively investigate the influence caused by the misalignment, we proposed a method for estimating the performance of a 4f-ONN in response to various misalignment in the context of the image classification task.The misalignment in numerical simulation is estimated by manipulating the optical intensity distributions in the fourth focus plane in the 4f system. Followed by a series of physical experiments to validate the simulation results. Using our method to test the impact of misalignment of 4f system on the classification accuracy of two popular image classification datasets, MNIST and Quickdraw16. On both datasets, we found that the performances of 4f-ONN generally degraded dramatically as the positioning error increased. Different positioning error tolerance in the misalignment orientations was observed over the two datasets. Classification performance could be preserved by positioning errors up to 200 microns in a specific direction.