Convolutional Neural Networks for Classifying Combinatorial Metamaterials

UvA-DARE (University of Amsterdam)

Abstract

This dataset contains the training and test data, as well as the trained neural networks as used for the paper 'Machine Learning of Combinatorial Rules in Mechanical Metamaterials', as published in XXX. In this paper, a neural network is used to classify each \(k \times k\) unit cell design into one of two classes (C or I). Additionally, the performance of the trained networks is analysed in detail. A more detailed description of the contents of the dataset follows below. NeuralNetwork_train_and_test_data.zip This file contains the train and test data used to train the Convolutional Neural Networks (CNNs) of the paper. Each unit cell size has its own file, and is saved in a zipped numpy file type (.npz). CNN_saves_kxk.zip This file contains the parameter configurations of the CNNs trained on \(k \times k\) unit cells. Every hyperparameter (number of filters nf, number of hidden neurons nh, learning rate lr) combination is saved separately. The neural networks can be loaded using Google's TensorFlow package in Python, specifically using the 'tf.keras.models.load_model' function.

Authors 4

1. Ryan van Mastrigt

   Institute for Atomic and Molecular Physics · University of Amsterdam

   Affiliation as printed

   University of Amsterdam; AMOLF

2. Marjolein Dijkstra

   Utrecht University

   Affiliation as printed

   Utrecht University

3. Martin van Hecke Aachen

   Leiden University · Institute for Atomic and Molecular Physics

   Affiliation as printed

   Leiden University; AMOLF

4. Corentin Coulais

   University of Amsterdam

   Affiliation as printed

   University of Amsterdam