Speaker:           Sk Habibullah 


Topic:             Symbolic Regression and Its Application


Date & Time:   Thursday, 1st April 2021 at 4:00 PM through MICROSOFT TEAMS 


Microsoft Teams Link:


  Join conversation




Symbolic regression is a powerful technique that can predict the model function and its parameters directly from the data set itself. Symbolic regression is now routinely used in computer science, physical sciences, material science, and social science. In this seminar, I will discuss symbolic regression and its application in science by two interesting methods. In the first method, I will show how genetic algorithms are used to generate requisite equations from data1,2. In the second method, I will discuss the physics-inspired recursive multidimensional symbolic regression algorithm, AI-Feynman method, which can solve big equations3. Lastly, I will show how symbolic regression can predict passive drug–membrane permeability coefficients by creating complex model functions4.





  1. Wang, Y. et al. MRS Commun., 2019, 9, 793-805.
  2. Gou, G. et al. Phy. Rev. B, 2011, 84, 144101.
  3. Udrescu, S. M. & Tegmark, M. Sci. Adv., 2020, 6, 2631.
  4. Dutta, A. et al.arXiv:2012.01766 [physics.chem-ph], 18 Jan 2021.