Fig. 4: Iris flower classification using the diffractive neural network.
From: Space-efficient optical computing with an integrated chip diffractive neural network
a Network consists of one layer. The outputs of the layer are the recognition results after the intensity detection. x1 is sepal length, x2 is sepal width, x3 is petal length, and x4 is petal width. y1 is Setosa, y2 is Versicolor, and y3 is Verginica. b Experimental output intensity distribution of the IDNN for a class of flowers as “Setosa” is demonstrated. c Training and testing results of classification. One classification error appears on the testing part. d Confusion matrix in our experiment using 30 different flowers.
