
Lecture 56 of 60 · Inverse Methods in Heat Transfer
NPTEL-NOC IITM
Inverse Methods in Heat Transfer · 60 lectures
60 lectures
2: Inverse Problems - Definition, History & Applications
3: The inverse Problem Solving Process
4: Review of Basic Heat Transfer for this Course
6: Introduction to Linear Regression for Inverse Problems
7: Example - Application of Linear Regression for an Inverse
8: Goodness of Fit & Coefficient of Determination
9: Linear Regression with Quadratic Model
12: Introduction to Normal Equations for Linear Models - Part 1
13: Normal Equations for Linear Models - Part 2
14: Parity Plots
15: Programming Inverse Methods using Normal Equations
16: Variants on the Linear Model for Inverse Problems
18: The General Inverse Methods Process
19: Simple Nonlinear Inverse Problem - Transient Heat Transfer
20: Review of Required Calculus Results
21: Gradient Descent Algorithm
22: Gradient Descent - Simple Example
23: Gradient Descent for Nonlinear Inverse Problem - Theory
25: Newton Algorithm for a System of Equations
26: Gauss Newton Algorithm - Derivation & Code
27: Overfitting & Regularization for Linear Models
28: Tikhonov Regularization & Levenberg Marquardt - Theory
29: Tikhonov & Levenberg Marquardt - Example Code
30: Introduction to Probability for Inverse Methods
31: Sum & Product Rules of Probability
32: Bayes Theorem - Simple Examples
33: Independence & Expectation
34: Variance & Covariance
35: Gaussian Distribution - The Standard Normal Table
36: Maximum Likelihood Estimate
37: MLE, MAP Estimates
38: Introduction to Bayesian Methods for Inverse Problems
39: Offline Bayesian Estimation
40: Offline Bayesian Estimation - MATLAB Demo
41: MHMCMC for Inverse Problems
42: MHMCMC for Inverse Problems - MATLAB Demo
43: Why Machine Learning in Inverse Heat Transfer?
44: Overview of AI & ML
45: Supervised Machine Learning as an Inverse Problem
46: Introduction to - From Linear Models to Neural Networks
47: Gradient Descent - Batch, Stochastic & Mini Batch
48: Logistic Regression - The Forward Model
49: Logistic Regression - Binary Entropy Cost Function
50: Multiclass Classification
51: Linear Separability & Neural Networks
52: Introduction to - XOR & Deeper Networks
53: Forward Pass Through a Simple Neural Network
54: Backprop in a Scalar Chain
55: Backprop in a MLP
56: Introduction to - ANNs as Surrogate Models
57: Physics Informed Neural Networks - Introduction
58: Physics Informed Neural Networks - An Intuitive Explanation
59: Physics Informed Neural Networks - BC Incorporation
60: PINNs for Inverse Problems
61: Introduction to - Sensitivity Analysis
62: Code Examples of Logistic Regression - OR & AND Gates
63: Code Example of Shallow Neural Network - XOR Gate
64: Code Walkthrough for PINNs in Burgers Equation
65: Formulation of a PINN Based Inverse Problem in Unsteady
66: Formulation of a Surrogate Model Based Inverse Solution