Figure 5
From: Freely scalable and reconfigurable optical hardware for deep learning
Experimentally measured 3-layer FC-NN output scores, otherwise known as confusion matrix, for 500 MNIST images from test dataset. The values along the diagonal represent correct classification by the model. Each column is an average of \(\sim 50\) vectors. (a) DONN output scores (no crosstalk correction applied). (b) Ground-truth (all-electronic) output scores. (c, d) Box plot of the diagonals of subfigures (a) and (b) respectively. (e) Difference in diagonals of DONN output scores versus ground-truth output scores. Box plots represent the median (orange), interquartile range (IQR, box) and ‘whiskers’ extending 1.5 IQRs beyond the first and third quartile; outliers are displayed as yellow circles.
