Lecture 12: Define ODEs Deep Neural Network | Section 3: Solving ODE Using PINNs | AI Technologies for Solving Ordinary Differential Equations | Products | Mohammad Samara Community

Lecture 12: Define ODEs Deep Neural Network

Lecture 12: Define ODEs Deep Neural Network

.

.

.

.

.

.

.

Lecture 12:

Define ODEs Deep Neural Network

AI Technologies for Solving Ordinary Differential Equations

Buy nowLearn more

Section 1 : Introduction

lecture 1: Introduction

lecture 2: Installing Anaconda

lecture 3: Install PyTorch CUDA

Section 2: Pytorch Basics

lecture 4: Deep Learning Theory

lecture 5: PyTorch Tensors Basics

lecture 6: Tensors to NumPy arrays

lecture 7: Backpropagation Theory

lecture 8: Backpropagation using PyTorch

Section 3: Solving ODE Using PINNs

Lecture 9: How PINNs Works

Lecture 10: Damped Harmonic Oscillator Exact Solution

Lecture 11: Coding the Exact Solution

Lecture 12: Define ODEs Deep Neural Network

Lecture 13: Set the Training Process

Lecture 14: Define the DNN Loss

Lecture 15: Results Evaluation

Lecture 16: Change the Loss Function

Lecture 17: Change the Network Size

Lecture 18: Full Code Summary

CODE

Section 4: Inverse Physics Informed Neural Networks (I-PINNs)

Lecture 19: Lets start with Inverse PINNs ODE

Lecture 20: Data Creation For the Inverse PINNs

Lecture 21: Define the IPINNS Network

Lecture 22: Set The Training Process

Lecture 23: Run the Training

Lecture 24: Results Review

Code

Section 5: Solving ODE Using Deep Neural Operator (DNO)

Lecture 25: Integration Data Creation

Lecture 26: Data Preprocessing Part 1

Lecture 27: Data Preprocessing Part 2

Lecture 28: Model Build Up

Lecture 29: Set The Training Process

Lecture 30: Results Review

CODE