Their method significantly outperforms the current state of the art in terms of data fitting (R^2), discovery rate (recovering the true relationship), and succinctness (output formula complexity). The authors show that their model is able to identify the underlying operators from data, achieving a high accuracy and AUC (91% and 0.96 on average resp.) for systems with as many as ten independent variables. The model was then applied to a variety of plausible relationships-both simulated and from physics and mathematics domains-involving different dimensions and constituents. This allowed to prior the exponentially large search with the predicted importance of the symbolic operators, which can significantly accelerate the discovery process. The novelty of this new approach is in (1) encoding the input data as an image with super-resolution, (2) developing an appropriate deep network pipeline, and (3) predicting the importance of each mathematical operator from the relationship image. Inspired by the incredible success of deep learning in computer vision, the authors tackle this problem by adapting various successful network architectures into the symbolic law discovery pipeline. This is not a trivial problem as it involves searching for a complex mathematical relationship over a large set of explanatory variables and operators that can be combined in an infinite number of ways. ![]() One of the most exciting applications of modern artificial intelligence is to automatically discover scientific laws from experimental data. Hengrui Xing Columbia University, Ansaf Salleb-Aouissi Columbia University, Nakul Verma Columbia University ![]() The conference promotes research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines.Īutomated Symbolic Law Discovery: A Computer Vision Approach Research from the department was accepted to the 35th AAAI Conference on Artificial Intelligence.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |