Fig 1.
Mach–Zehnder interferometer with a light modulator on each arm.
The occupation number options for the two photons at different stages are shown. The interferometer includes: (1) two 50:50 beam splitters with input ports (red: 1,2) and output ports (red: 3,4); (2) two photon-number resolving detectors; (3) two light modulators implementing and
; (4) two mirrors; (5) a coincidence counter detecting: (i) two photons at port 3, (ii) two at port 4, or (iii) one at each port. This counter determines the output function f.
Fig 2.
Schematic architecture of a QONN with L layers implemented using Mach–Zehnder QONs.
Blue lines indicate electrical connections; green lines indicate laser paths. Each layer is color-coded. In the first layer (pink), the right-side light modulators are governed by input data, while weights govern the left-side light modulators. In deeper layers, right-side light modulators are driven by the outputs of the previous layer. QON outputs also feed the weight module for training. For clarity, not all connections are shown.
Fig 3.
Training and test accuracy and loss for all pre-activation functions in the MNIST binary classification task (class 0 vs 1).
Ideal (top) and non-ideal (bottom) scenarios are shown. Curves represent the mean over five runs; shaded bands denote the standard deviation.
Fig 4.
Training and test accuracy and loss for all pre-activation functions in the FashionMNIST binary classification task (class 0 vs 1).
Ideal (top) and non-ideal (bottom) scenarios are shown. Mean over five runs with standard deviation.
Fig 5.
Multiclass MNIST (10 classes).
Training and test accuracy and loss under ideal (top) and non-ideal (bottom) conditions. Curves represent the mean over five runs with standard deviation.
Fig 6.
Multiclass FashionMNIST (10 classes).
Training and test accuracy and loss under ideal (top) and non-ideal (bottom) conditions. Mean over five runs with standard deviation.