Mohammad Samara/PINNs Using Physics-Nemo [Modulus ]

PINNs Using Physics-Nemo [Modulus ]

  • Course
  • 60 Lessons

Easy Simulations with AI

  • 10 hours on-demand video

  • Certificate of completion

  • Full access

55$ Special Discount price : 10$

What you'll learn

  • Build PINNs based pdes solver.

  • Understand the Theory behind PINNs PDEs solvers.

  • Build models using NVIDIA Modulus

  • Deploy NVIDIA Modulus useing GoogleColab and your own NVIDIA GPU

Contents

Section 1: Introduction

lecture 1: Introduction
Preview
lecture 2: Course Structure
Preview
lecture 3: Deep Learning Theory
lecture 4: PINNs Theory
ref.txt

Section2: PINNs Solution for 1D Burgers Equation with Pytorch

Section-2 Files
lecture 5: Define the Neural Network
lecture 6: Initial Conditions and Boundary Conditions
lecture 7: Optimizer
lecture 8: Loss Function
lecture 9: Train the Model
lecture 10: Results Evaluation

Section 3: 1D Wave Equation

Section-3 Files
lecture 11: What is the Wave Equation
Preview
lecture 12: Setting Up Google Colab
lecture 13: Define the Wave Equation Function
lecture 14: Define the Config File
lecture 15: Import Needed Libraries
lecture 16: Set Up the main RUN File
lecture 17: Define the B.C, Interior Points
lecture 18: Add Validator Functionality
lecture 19: Solve
lecture 20: Results Extraction
lecture 21: Results Post Processing

Section 4: Cavity Flow

Section-4 Files
lecture 22: Setting up env. in your personal computer
lecture 23: Cavity Flow Problem
lecture 24: Define the Config File
lecture 25: Import Needed Libraries
lecture 26: Set Up the main RUN File
lecture 27: Define the Navier-Stokes equation and DNN
Preview
lecture 28: Define the B.C, I.C, Interior Points
lecture 29: Solve
lecture 30: Results Extraction
lecture 31: Results Post Processing
lecture 32: Pretrained Model Inference

Section 5: 2D Heat Sink

Section-5 Files
lecture 33: 2D heat channel problem
lecture 34: Define the Config File
Preview
lecture 35: Import Needed Libraries
lecture 36: Set Up the main RUN File
lecture 37: Define the geometry
lecture 38: Define the Navier-Stokes equation and DNN
lecture 39: Define the B.C, Interior Constraints
lecture 40: Add Monitor
lecture 41: Solve
lecture 42: Results Extraction
lecture 43: Results Post Processing
Preview

Section 6: 2D Stress Analysis

Section-6 Files
lecture 44: 2D Stress Analysis Problem
lecture 45: Define the Config File
lecture 46: Import Needed Libraries
lecture 47: Define the DNN
lecture 48: Define the geometry - part a
lecture 49: Define the geometry - part b
lecture 50: Set Changing Parameters
lecture 51: Define the B.C, Interior Constraints
lecture 52: Case Inferencing
lecture 53: Solve
lecture 54: Results Post Processing

Requirements

  • High School Math

  • Basic Python knowledge

Description

Description

This is a introductory course that will prepare you to work with Physics-Informed Neural Networks (PINNs) using NVIDIA Modulus. We will cover the fundamentals of Solving partial differential equations (PDEs) using Physics-Informed Neural Networks (PINNs) from its basics and March towards solving PINNs with Nvidia modulus.

What skills will you Learn:

In this course, you will learn the following skills:

  • Understand the Math behind solving partial differential equations (PDEs) with PINNs.

  • Write and build Machine Learning Algorithms to solve PINNs using Pytorch.

  • Write and build Machine Learning Algorithms to solve PINNs using Nvidia Modulus.

  • Postprocess the results.

  • Use opensource libraries.

  • Define your own PDEs to solve them or use built in equations (such as the N.S equations in Nvidia Modulus).

We will cover:

  • How to deploy Nvidia Modulus on your own computer GPU and in Google Collab.

  • Physics-Informed Neural Networks (PINNs) Solution for 1D Burgers Equation using pytorch.

  • Physics-Informed Neural Networks (PINNs) Solution for  1D wave Equation using Nvidia modulus.

  • Physics-Informed Neural Networks (PINNs) Solution for  cavity flow problem using Nvidia modulus.

  • Physics-Informed Neural Networks (PINNs) Solution for  2D heat sink flow problem using Nvidia modulus.

If you do not have prior experience in Machine Learning or Computational Engineering, that's no problem. This course is complete and concise, covering the fundamentals of Machine Learning/ Physics-Informed Neural Networks (PINNs). Let's enjoy Learning Nvidia Modulus together.


Hear from our happy students

"Excellent!!!!"

Srinivasan Palanichamy

"Its good for the first steps of the process we wait for the next lesson for Pinns in modulus, keep up the good work"

Michail Athanasiou

"Easy way to do it..."

Sara Harmon

"good"

June Alba