Skip navigation
Please use this identifier to cite or link to this item:
Title: MLP neural network trained on the QCL [-2, +3] Å dataset
Contributors: Correa Hernandez, Andres
Gmachl, Claire F
Keywords: quantum cascade laser, mid-infrared, figure of merit, machine learning, multi-layer perceptron, neural network, regression
Issue Date: 16-Feb-2024
Publisher: Princeton University
Abstract: This item contains two files. A multi-layer perceptron (MLP) neural network is built using the MATLAB Deep Network Designer (.m file). It imports a quantum cascade laser (QCL) dataset and splits it into 70% training, 15% validation, and 15% testing subsets. The network consists of an input layer, three hidden layers (each having a normalization and activation layer), and a regression output layer. All of the layers are fully connected, and the root-mean-square error (RMSE) is used to evaluate the accuracy of the network. An algorithm is trained on the [-2, +3] QCL dataset using 50 neurons, ReLU activation function, solver Adam, 0.001 learning rate, over 150 epochs, and is saved to be used in the prediction of figure of merit values for QCL designs (.mat file).
Description: Details on building machine learning algorithms for QCL design can be found in [1] and the [-2, +3] Å QCL dataset can be found in [2]. References: [1] A. C. Hernandez and C. F. Gmachl, “Application of Machine Learning to Quantum Cascade Laser Design,” in 2023 57th Annual Conference on Information Sciences and Systems, CISS 2023, 2023. doi: 10.1109/CISS56502.2023.10089756. [2] A. Correa Hernandez, C. F. Gmachl, and M. Lyu, “QCL Dataset, 10 Layer Structure, Tolerance [-2, +3] A, Electric Field [0,10,150] kV/cm.” Princeton University, Princeton, 2023. doi:
Appears in Collections:EE Research Data Sets

Files in This Item:
File Description SizeFormat 
README.txt3.35 kBTextView/Download
mlp_reg_train.mmulti-layer perceptron neural network designer code3 kBMATLABView/Download
adam_relu_hidden_3_neuron_50_epoch_150_net.matTrained neural network using [-2, +3] QCL dataset27.93 kBMATLABView/Download

Items in Dataspace are protected by copyright, with all rights reserved, unless otherwise indicated.