Skip to content
View mjayadharan's full-sized avatar
  • Northwestern University
  • Chicago

Block or report mjayadharan

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 250 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
mjayadharan/README.md

ezgif com-gif-maker (2)

Hey ๐Ÿ‘‹, I'm Manu


LinkedInย  Gmailย  ResearchGateย 


My background in a nutshell.


  • I am an applied mathematician with research interests spanning a wide range of quantitative scientific fields. My interests include developing numerical methods for data-driven inverse problems involving differential equations, high-performance solvers for PDEs, and financial modeling. I have a Ph.D. in Mathematics with a focus on numerical analysis and high-performance computing for PDEs. I worked on Wall Street as a quant after completing my PhD before deciding to pursue a career in research.
  • I have experience in developing and implementing novel algorithms to solve multiphysics CFD problems, using both data-driven deep learning techniques and classical mixed finite element methods (FEM).
  • Currently, I work as a credit quant specializing in pricing and risk management of credit derrivatives in the risk-neutral framework, specifically in LATAM emerging markets.
  • I love working on new challenging models and implementing them, while collaborating with others.
  • Always looking for new collaborators and interesting projects.

Languages I work with:

  • Python for general purpose programming and ML software development.
  • C++ for high performance scientific computing and simulations.

Mathematical Skills:

  • Numerical Analysis.
  • Inverse PDE.
  • Data Driven Differential Equation Discovery.
  • HPC Parallel computing.
  • Advanced Probability, Statistics.
  • ML,DL.
  • Biocomputing.
  • Math Finance and Stochastic Calculus.
  • Risk Neutral Pricing and Hedging of Credit derrivatives.
  • Bonds, CDS, XCCY swaps.
  • CFD Computational Fluid Dynamics.

Software packages I currently use:

  • ML/ Data Science: Numpy, Pandas, Jupyter, Keras-Tensorflow2
  • Visualization: Matplotlib, ParaView, gnuplot.
  • Scientific computing: deal.II, FreeFem++, phoenix.
  • My favorite editors and IDEs: Eclipse, Jupyter notebook, Colab, Emacs.

Languages and packages I used to work with:

  • Fortran, Matlab, PyTorch, Scikit-learn

Checkout some of my recent projects and preprints:


Machine Learning:

  1. DaeFinder: DaeFinder is a Python package designed to discover Differential Algebraic Equations (DAEs) from noisy data using sparse optimization framework.
  2. Fluidlearn: A python based package to solve fluid flow PDEs using deep learning techniques.
  3. Hands on practical ML projects:

High performance scientific computing:

  1. [Space-time-DD](https://github.com/mjayadharan/MMMFE-ST-DD: A C++ based fluid flow simulator using multiscale space-time domain.
  2. Poroelastic flow simulator: C++ based poroelastic fluid flow simulator using MPI.

Other open-source contributions:

  1. FEM package deal.II: Most of the HPC packages I have written uses deal.II and I am also one of the contributors to this popular open-source FEM package.

Recent preprint:

  1. Parallel computations to solve poroelastic flow: M. Jayadharan, E. Khattatov, I. Yotov, Domain decomposition and partitioning methods for mixed finite element discretization of the Biot system of poroelasticity, arxiv math.NA, 2010.15353.

Thank You-๐Ÿ™๐Ÿผ

Pinned Loading

  1. FluidLearn FluidLearn Public

    Software to solve PDEs and estimate physical parameters governing fluid flow using Deep learning techniques.

    Jupyter Notebook 4 4

  2. MMMFE-ST-DD MMMFE-ST-DD Public template

    Fluid flow simulator using MFEM and multiscale space-time sub-domains.

    C++ 4 1

  3. ML_mini_projects ML_mini_projects Public

    Repository containing several mini projects, implementing small scale ML training models using scikit-learn, tensorflow and kern. Mainly for the purpose of education and fun.

    Jupyter Notebook 1 1

  4. BiotDD BiotDD Public

    Repository containing deal.ii implementation of domain decomposition for Biot system of poroelasticity

    C++ 1 1

  5. Biological-VTNNS Biological-VTNNS Public

    Code archive of Variable Topology Neural Network Simulator (VTNNS) based on LIF model.

    Fortran

  6. dealii/dealii dealii/dealii Public

    The development repository for the deal.II finite element library

    C++ 1.6k 797