Student Seminar: SK Habibullah

STUDENT SEMINAR 

 

 

Speaker:           Sk Habibullah 

 

Topic:             Symbolic Regression and Its Application

 

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

 

Microsoft Teams Link:

https://teams.microsoft.com/l/meetup-join/19%3a95b3dfced9714083b3ea8ab65a1c6082%40thread.tacv2/1617079648182?context=%7b%22Tid%22%3a%226f15cd97-f6a7-41e3-b2c5-ad4193976476%22%2c%22Oid%22%3a%2213f7ab10-7e6d-4a30-a1d3-1e99669813b6%22%7d

 

Join conversation teams.microsoft.com

 

Abstract:

 

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 data^1,2. 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.

 

 

References:

 

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.