Taufeq is a Research Assistant at the Collaboratory for Advanced Computing and Simulations at the University of Southern California, Los Angeles. He has specialized in fluids and computational science and has been working on data-driven solutions of partial differential equations for problems in science and engineering.
His expertise is in developing high performance numerical simulation codes for parallel and heterogeneous architectures for accurate visualization and optimization.
He is also led teams to advance their technical stacks and digital presence while contributing across research labs, multidisciplinary research initiatives and course materials.
Taufeq holds dual master degrees in Computer Science and Mechanical Engineering from the University of Southern California. He is also a graduate of Osmania University, from where he earned his bachelor in engineering with high distinction.
He is fluent in English, Hindi/Urdu and German.
Physics Informed Neural Networks for Molecular Dynamics Applications
T. M. Razakh, B. Wang, S. Jackson, K. Nomura, A. Nakano, R. Kalia & P. Vashishta
Mork Family Department Symposium, University of Southern California (2020)
Zmate is a tool for students taking classes online. Where every course instructor has their own zoom link, there comes the addition of office hours and study sessions - which makes it hard to keep track of those links. Zmate is a centralized repository for all your course related meetings for a semester where your professors and TA’s post all the necessary links to your personal calendar. Ruby on Rails, HTML, CSS, Heroku
A VR game which teaches you KungFu from basics. Designed to work with HTC VIVE head mount displays. Makes use of Unity Game Engine
We have developed a novel differential equation solver software called PND based on the physics-informed neural network for molecular dynamics simulators. Based on automatic differentiation technique provided by Pytorch, our software allows users to flexibly implement equation of atom motions, initial and boundary conditions, and conservation laws as loss function to train the network. PND comes with a parallel molecular dynamics (MD) engine in order for users to examine and optimize loss function design, and different conservation laws and boundary conditions, and hyperparameters, thereby accelerate the PINN-based development for molecular applications.
Taufeq Mohammed Razakh, Beibei Wang, Shane Jackson, Rajiv K. Kalia, Aiichiro Nakano, Ken-ichi Nomura, Priya Vashishta
University of Southern California
Osmania University