Fig. 4: Deep learning model layout. | Microsystems & Nanoengineering

Fig. 4: Deep learning model layout.

From: Finding the optical properties of plasmonic structures by image processing using a combination of convolutional neural networks and recurrent neural networks

Fig. 4

The boxes show the filters used in each layer. A total of 500 epochs were run in the training stage, with a learning rate of 0.0001 and Nesterov Adam as an optimizer. This model is a combination of a ResNet CNN model and an RNN model. The output is from the final fully connected layer with 1000 nodes, where each node is a frequency point in the absorption curve

Back to article page