TY  - JOUR
AU  - Barenboim, G.
AU  - Hirn, J.
AU  - Sanz, V.
PY  - 2021
DA  - 2021//
TI  - Symmetry meets AI
T2  - SciPost Phys.
JO  - Scipost Physics
SP  - 014
EP  - 11pp
VL  - 11
IS  - 1
PB  - Scipost Foundation
AB  - We explore whether Neural Networks (NNs) can discover the presence of symmetries as they learn to perform a task. For this, we train hundreds of NNs on a 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.
SN  - 2542-4653
UR  - https://arxiv.org/abs/2103.06115
UR  - https://doi.org/10.21468/SciPostPhys.11.1.014
DO  - 10.21468/SciPostPhys.11.1.014
LA  - English
N1  - WOS:000680039500002
ID  - Barenboim_etal2021
ER  -