Skip to main content
. Author manuscript; available in PMC: 2021 Jan 1.
Published in final edited form as: IEEE J Sel Top Quantum Electron. 2019 Jun 6;26(1):3700114. doi: 10.1109/JSTQE.2019.2921376

Fig. 1.

Fig. 1.

All-optical D2NN-based classifiers. These D2NN designs were based on spatially and temporally coherent illumination and linear optical materials/layers. (a) D2NN setup for the task of classification of handwritten digits (MNIST), where the input information is encoded in the amplitude channel of the input plane. (b) Final design of a 5-layer, phase-only classifier for handwritten digits. (c) Amplitude distribution at the input plane for a test sample (digit “0’). (d-e) Intensity patterns at the output plane for the input in (c); (d) is for MSE-based, and (e) is softmax-cross-entropy (SCE)-based designs. (f) D2NN setup for the task of classification of fashion products (Fashion-MNIST), where the input information is encoded in the phase channel of the input plane. (g) Same as (b), except for fashion product dataset. (h) Phase distribution at the input plane for a test sample. (i-j) Same as (d) and (e) for the input in (h). λ refers to the illumination source wavelength. Input plane represents the plane of the input object or its data, which can be generated by another optical imaging system or a lens, projecting an image of the object data onto this plane.