20.500.12556/RUL-153002 Efficient generator of mathematical expressions for symbolic regression We propose an approach to symbolic regression based on a novel variational autoencoder for generating hierarchical structures, HVAE. It combines simple atomic units with shared weights to recursively encode and decode the individual nodes in the hierarchy. Encoding is performed bottom-up and decoding top-down. We empirically show that HVAE can be trained efficiently with small corpora of mathematical expressions and can accurately encode expressions into a smooth low-dimensional latent space. The latter can be efficiently explored with various optimization methods to address the task of symbolic regression. Indeed, random search through the latent space of HVAE performs better than random search through expressions generated by manually crafted probabilistic grammars for mathematical expressions. Finally, EDHiE system for symbolic regression, which applies an evolutionary algorithm to the latent space of HVAE, reconstructs equations from a standard symbolic regression benchmark better than a state-of-the-art system based on a similar combination of deep learning and evolutionary algorithms. symbolic regression equation discovery generative models variational autoencoders evolutionary algorithms simbolna regresija odkrivanje enačb generativni modeli variacijski samokodirniki evolucijski algoritmi true false true Angleški jezik Slovenski jezik Članek v reviji 2023-12-14 08:56:19 2023-12-14 08:56:23 2023-12-15 03:49:24 0000-00-00 00:00:00 2023 0 0 Str. 4563-4596 iss. 11 Vol. 112 Nov. 2023 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.8 1573-0565 10.1007/s10994-023-06400-2 176785923 s10994-023-06400-2_(1).pdf s10994-023-06400-2_(1).pdf 1 932B365764766DC41A7856614D8FA66D b24ba28bb34bb2894a2b1c83a3717532b522c55d6d1f20a42863eb1332e0c9ab 73401a35-9a57-11ee-91f8-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=178780 https://link.springer.com/article/10.1007/s10994-023-06400-2 0 4771144e-9a56-11ee-91f8-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=178775 Fakulteta za matematiko in fiziko 0 0 0