Physics Informed Neural Networks (PINNs)

Focused View

Dr.Mohammad Samara

6:15:57

163 View

1. Introduction

1. Introduction.mp4

02:30

2.1 ref.txt

2. Installing Anaconda.mp4

05:46

3.1 ref.txt

3. Course Structure.mp4

07:43

2. FDM Numerical Solution 1D Heat Equation

1. Numerical solution theory.mp4

12:54

2.1 heat main.zip

2. Pre-processing.mp4

16:42

3.1 heat main.zip

3. Solving the Equation.mp4

10:34

4.1 heat main.zip

4. Post-processing.mp4

04:56

3. FDM Numerical Solution for 2D Burgers Equation

1.1 burgers 2d main.zip

1. Pre-processing.mp4

24:06

2.1 burgers 2d main.zip

2. Solving the Equation.mp4

09:18

3.1 burgers 2d main.zip

3. Post-processing.mp4

06:32

4. PINNs Solution for 1D Burgers Equation

1. PINNs Theory.mp4

08:30

2. Deep Learning Theory.mp4

11:12

3.1 burgers 1d main.zip

3. Define the Neural Network.mp4

10:42

4.1 burgers 1d main.zip

4. Initial Conditions and Boundary Conditions.mp4

24:42

5.1 burgers 1d main.zip

5. Loss Function.mp4

18:08

6.1 burgers 1d main.zip

6. Train the Model.mp4

12:06

7.1 burgers 1d main.zip

7. Optimizer.mp4

06:31

8.1 burgers 1d main.zip

8. Results Evaluation.mp4

08:56

5. PINNs Solution for 2D Heat Equation

1.1 heat 2d pinns main.zip

1. Define the Neural Network.mp4

09:05

2.1 heat 2d pinns main.zip

2. Initial Conditions and Boundary Conditions.mp4

15:05

3.1 heat 2d pinns main.zip

3. Optimizer.mp4

12:23

4.1 heat 2d pinns main.zip

4. Loss Function.mp4

16:57

5.1 heat 2d pinns main.zip

5. Train the Model.mp4

04:02

6.1 heat 2d pinns main.zip

6. Results Evaluation.mp4

08:33

6. Deepxde Solution for 1D Heat

1.1 deepxde 1d heat main.zip

1. Set Geometry, B.C and I.C.mp4

24:45

2.1 deepxde 1d heat main.zip

2. Define the Network and the PDE.mp4

10:12

3.1 deepxde 1d heat main.zip

3. Train the model.mp4

06:02

4.1 deepxde 1d heat main.zip

4. Result evaluation.mp4

02:32

7. Deepxde Solution for 2D Navier Stokes

1.1 ns deepxde main.zip

1. Set Geometry.mp4

12:32

2.1 ns deepxde main.zip

2. Set Boundary Conditions.mp4

18:00

3.1 ns deepxde main.zip

3. Define the Network and the PDE.mp4

19:06

4.1 ns deepxde main.zip

4. Train the model.mp4

05:03

5.1 ns deepxde main.zip

5. Result evaluation.mp4

09:52

Description

Simulations with AI

What You'll Learn?

Understand the Theory behind PDEs equations solvers.
Build numerical based PDEs solver.
Build PINNs based pdes solver.
Understand the Theory behind PINNs PDEs solvers.

Who is this for?

Engineers and Programmers whom want to Learn PINNs

What You Need to Know?

High School Math

Basic Python knowledge

More details

Description
Description
This is a complete course that will prepare you to use Physics-Informed Neural Networks (PINNs). We will cover the fundamentals of Solving partial differential equations (PDEs) and how to solve them using finite difference method as well as Physics-Informed Neural Networks (PINNs).

What skills will you Learn:
In this course, you will learn the following skills:
Understand the Math behind Finite Difference Method .
Write and build Algorithms from scratch to sole the Finite Difference Method.
Understand the Math behind partial differential equations (PDEs).
Write and build Machine Learning Algorithms to solve PINNs using Pytorch.
Write and build Machine Learning Algorithms to solve PINNs using DeepXDE.
Postprocess the results.
Use opensource libraries.

We will cover:
Finite Difference Method (FDM) Numerical Solution 1D Heat Equation.
Finite Difference Method (FDM) Numerical Solution for 2D Burgers Equation.
Physics-Informed Neural Networks (PINNs) Solution for 1D Burgers Equation.
Physics-Informed Neural Networks (PINNs) Solution forÂ 2D Heat Equation.
DeepxdeÂ Solution for 1D Heat.
DeepxdeÂ Solution forÂ 2D Navier Stokes.

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/ partial differential equations (PDEs) Physics-Informed Neural Networks (PINNs). Let's enjoy Learning PINNs together.
Who this course is for:
Engineers and Programmers whom want to Learn PINNs

User Reviews

Rating

average 0

Total votes0

Focused display

11 Years experience in Computation Models building, since 7 year I am mainly focused on the use of Data to build machine learning based models, to solve practical Industry problems such as data analysis, Value prediction, performance classification (abnormality detection), and applying Machine Learning to machine vision problems as well as system control and behavior mapping via Reinforcement learning using data collected from the testing and simulation.I Have a Phd and masters From the University of Tokyo, and worked in several Japanese and International companies, currently I am working in Panasonic as a Data Science/Machine Learning Expert (Job Rank: Chief Engineer).I am absolutely passionate about Data Science use in Engineering companies and I am looking forward to sharing my passion and knowledge with you!

Udemy

View courses Udemy

Students take courses primarily to improve job-related skills.Some courses generate credit toward technical certification. Udemy has made a special effort to attract corporate trainers seeking to create coursework for employees of their company.