AI Capable of Predicting Properties of Multifaceted Metamaterials

Can a three-dimensional (3D) piece of origami be flattened without damaging it? Merely by looking at the piece, the answer is difficult to predict because every fold in the origami has to be well-suited for flattening. This is an instance of a combinatorial problem. A new study by the University of Amsterdam's (UvA) Institute of Physics and research institute AMOLF has shown that machine learning algorithms can exactly and efficiently answer these types of questions. This hopefully will give a boost to the artificial intelligence (AI)-supported design of complex and functional (meta)materials.