Orthogonality of diffractive deep neural network
Shuiqin Zheng, Shixiang Xu, Dianyuan Fan
Abstract
Some rules of the diffractive deep neural network (D 2 NN) are discovered. They reveal that the inner product of any two optical fields in D 2 NN is invariant and the D 2 NN acts as a unitary transformation for optical fields. If the output intensities of the two inputs are separated spatially, the input fields must be orthogonal. These rules imply that the D 2 NN is not only suitable for the classification of general objects but also more suitable for applications aimed at optical orthogonal modes. Our simulation shows the D 2 NN performs well in applications like mode conversion, mode multiplexing/demultiplexing, and optical mode recognition.
Topics & Concepts
OrthogonalityMultiplexingArtificial neural networkOpticsComputer scienceInvariant (physics)Unitary transformationOptical computingMode (computer interface)Unitary statePhysicsArtificial intelligenceTelecommunicationsMathematicsLawQuantum mechanicsQuantumGeometryOperating systemMathematical physicsPolitical scienceNeural Networks and Reservoir ComputingOptical Network TechnologiesPhotonic and Optical Devices