Symmetry meets AI
This work addresses the problem of understanding how neural networks learn underlying patterns like symmetry, with potential applications in art analysis, but it is incremental as it builds on existing methods for symmetry detection.
The study investigated whether neural networks can autonomously discover symmetries while learning a task, using a decoy task based on physics templates without symmetry information, and found that the networks identified symmetry information, which was then applied to classify symmetry levels in paintings by artists like Picasso, Pollock, and Van Gogh.
We explore whether Neural Networks (NNs) can {\it discover} the presence of symmetries as they learn to perform a task. For this, we train hundreds of NNs on a {\it decoy task} based on well-controlled Physics templates, where no information on symmetry is provided. We use the output from the last hidden layer of all these NNs, projected to fewer dimensions, as the input for a symmetry classification task, and show that information on symmetry had indeed been identified by the original NN without guidance. As an interdisciplinary application of this procedure, we identify the presence and level of symmetry in artistic paintings from different styles such as those of Picasso, Pollock and Van Gogh.