
Lecture 76 of 84 · ML for Engineering and Science
NPTEL-NOC IITM
ML for Engineering and Science · 84 lectures
84 lectures
1: Introduction to the Course History of Artificial Intelligence
2: Overview of Machine Learning
3: Why Linear Algebra ? - Scalars, Vectors, Tensors
4: Basic Operations - Machine Learning for Engineering
5: Norms - Machine Learning for Engineering & Science
6: Linear Combinations - Span Linear Independence
7: Matrix Operations Special Matrices Matrix Decompositions
8: Introduction to Probability Theory Discrete & Continuous
9: Conditional - Joint - Marginal Probabilities Sum Rule
10: Bayes’ Theorem - Simple Examples
11: Independence Conditional Independence Chain Rule Of
12: Expectation - Machine Learning for Engineering & Science
13: Variance Covariance - Machine Learning for Engineering
14: Some Relations for Expectation & Covariance
15: Machine Representation of Numbers - Overflow - Underflow
16: Derivatives - Gradient - Hessian - Jacobian - Taylor Series
17: Matrix Calculus - Slightly Advanced
18: Optimization - Part 1 - Unconstrained Optimization
20: Introduction to Numerical Optimization Gradient Descent
21: Gradient Descent - Part 2 - Proof - Numerical Gradient
22: Introduction to Packages - Machine Learning
23: The Learning Paradigm - Machine Learning for Engineering
24: A Linear Regression Example
25: Linear Regression - Least Squares - Gradient Descent
26: Coding Linear Regression - Machine Learning
27: Generalized Function for Linear Regression
28: Goodness of Fit - Machine Learning for Engineering
29: Bias Variance Trade Off - Machine Learning for Engineering
30: Gradient Descent Algorithms
31: Introduction to - Deep Learning
32: Logistic Regression - Machine Learning for Engineering
33: Binary Entropy Cost Function
34: OR Gate Via Classification
36: XOR Gate - Machine Learning for Engineering & Science
38: Gradient of Logistic Regression
42: Multinomial Classification - Softmax
47: Introduction to Back Prop
49: Introduction to Convolution Neural Networks (CNN)
50: Types of Convolution - Machine Learning for Engineering
51: CNN Architecture - Part 1 - LeNet & Alex Net
52: CNN Architecture - Part 2 - VGG Net
53: CNN Architecture - Part 3 - GoogleNet
54: CNN Architecture - Part 4 - ResNet
55: CNN Architecture - Part 5 - DenseNet
56: Train Network for Image Classification
57: Semantic Segmentation - Machine Learning for Engineering
58: Hyperparameter Optimization
59: Transfer Learning - Machine Learning for Engineering
60: Segmentation of Brain Tumors from MRI using Deep Learning
62: Learning Rate Decay - Weight Initialization
63: Data Normalization - Machine Learning for Engineering
64: Batch Norm - Machine Learning for Engineering & Science
65: Introduction to RNNs - Machine Learning for Engineering
66: Example - Sequence Classification
67: Training RNNs - Loss & BPTT
68: Vanishing Gradients & TBPTT
69: RNN Architectures - Machine Learning for Engineering
70: LSTM - Machine Learning for Engineering & Science
72: Deep RNNs & Bi RNNs - Machine Learning for Engineering
75: Knn - Machine Learning for Engineering & Science
76: Binary Decision Trees - Machine Learning for Engineering
77: Binary Regression Trees - Machine Learning for Engineering
78: Bagging - Machine Learning for Engineering & Science
80: Boosting - Machine Learning for Engineering & Science
81: Gradient Boosting - Machine Learning for Engineering
82: Unsupervised Learning & Kmeans
83: Agglomerative Clustering - Machine Learning
84: Probability Distributions - Gaussian - Bernoulli
87: Naive Bayes - Machine Learning for Engineering & Science
90: PCA - Part 2 - Machine Learning for Engineering & Science
91: Support Vector Machines - Machine Learning for Engineering
92: MLE - MAP & Bayesian Regression
93: Introduction to Generative Model
94: Generative Adversarial Networks (GAN)
95: Variational Auto Encoders (VAE)
96: Applications - Cardiac MRI - Segmentation & Diagnosis
97: Applications - Cardiac MRI Analysis
98: Introduction to - Machine Learning for Engineering
99: Application - Part 1 - Description - Fin Heat Transfer
100: Application - Part 1 - Solution - Description
101: Application - Part 2 - Description
102: Application - Part 2 - Solution
105: Application - Part 4 - Solution of PDE/ODE using Neural
106: Summary & Road Ahead - Machine Learning for Engineering