What is it about?

The interferometer is a fundamental building block of optical neural networks, however, its nonlinear response limits the accuracy. We demonstrated linearized interferometers that can provide 2 to 3 more bits of precision. The device can directly replace existing interferometers without adding complexity, and the corresponding optical neural network shows higher training accuracy.

Featured Image

Why is it important?

The conventional interferometer has a sinusoidal transfer function, which leads to inevitable dynamic phase errors. We introduced a superlinear phase change to compensate for the sublinear sinusoidal function, therefore achieving a much more linear response over its entire range.


The linearized interferometer is an ideal operator for analog optical signal processing. Thanks to the same simple phase control and much less phase quantization error, it has great potential to scale up for large-size photonic circuits such as optical neural networks. Moreover, the laxer criteria of the device structure allow it to easily accommodate fabrication deviations and can directly replace existing interferometers.

Yuan Yuan
Hewlett Packard Enterprise Co

Read the Original

This page is a summary of: Low-phase quantization error Mach–Zehnder interferometers for high-precision optical neural network training, APL Photonics, April 2023, American Institute of Physics, DOI: 10.1063/5.0146062.
You can read the full text:




The following have contributed to this page