Fig. 7: Classification performance on CIFAR-10. | Nature Communications

Fig. 7: Classification performance on CIFAR-10.

From: Ultra-broadband all-optical nonlinear activation function enabled by MoTe2/optical waveguide integrated devices

Fig. 7

The CIFAR-10 dataset (Canadian Institute For Advanced Research) is a collection of images that are commonly used to train machine learning and computer vision algorithms. a ONN architecture for the CIFAR-10 classification task. b, c Confusion matrices for the NAF test dataset constructed from the saturable absorption and reverse saturable absorption properties of MoTe2.

Back to article page