NOC:Machine Learning for Engineering and Science Applications


Lecture 1 - Introduction to the Course History of Artificial Intelligence


Lecture 2 - Overview of Machine Learning


Lecture 3 - Why Linear Algebra ? Scalars, Vectors, Tensors


Lecture 4 - Basic Operations


Lecture 5 - Norms


Lecture 6 - Linear Combinations Span Linear Independence


Lecture 7 - Matrix Operations Special Matrices Matrix Decompositions


Lecture 8 - Introduction to Probability Theory Discrete and Continuous Random Variables


Lecture 9 - Conditional, Joint, Marginal Probabilities Sum Rule and Product Rule Bayes' Theorem


Lecture 10 - Bayes' Theorem - Simple Examples


Lecture 11 - Independence Conditional Independence Chain Rule Of Probability


Lecture 12 - Expectation


Lecture 13 - Variance Covariance


Lecture 14 - Some Relations for Expectation and Covariance (Slightly Advanced)


Lecture 15 - Machine Representation of Numbers, Overflow, Underflow, Condition Number


Lecture 16 - Derivatives,Gradient,Hessian,Jacobian,Taylor Series


Lecture 17 - Matrix Calculus (Slightly Advanced)


Lecture 18 - Optimization 1 Unconstrained Optimization


Lecture 19 - Introduction to Constrained Optimization


Lecture 20 - Introduction to Numerical Optimization Gradient Descent - 1


Lecture 21 - Gradient Descent 2 Proof of Steepest Descent Numerical Gradient Calculation Stopping Criteria


Lecture 22 - Introduction to Packages


Lecture 23 - The Learning Paradigm


Lecture 24 - A Linear Regression Example


Lecture 25 - Linear Regression Least Squares Gradient Descent


Lecture 26 - Coding Linear Regression


Lecture 27 - Generalized Function for Linear Regression


Lecture 28 - Goodness of Fit


Lecture 29 - Bias-Variance Trade Off


Lecture 30 - Gradient Descent Algorithms


Lecture 31 - Introduction to Week 5 (Deep Learning)


Lecture 32 - Logistic Regression


Lecture 33 - Binary Entropy cost function


Lecture 34 - OR Gate Via Classification


Lecture 35 - NOR, AND, NAND Gates


Lecture 36 - XOR Gate


Lecture 37 - Differentiating the sigmoid


Lecture 38 - Gradient of logistic regression


Lecture 39 - Code for Logistic Regression


Lecture 40 - Multinomial Classification - Introduction


Lecture 41 - Multinomial Classification - One Hot Vector


Lecture 42 - Multinomial Classification - Softmax


Lecture 43 - Schematic of multinomial logistic regression


Lecture 44 - Biological neuron


Lecture 45 - Structure of an Artificial Neuron


Lecture 46 - Feedforward Neural Network


Lecture 47 - Introduction to back prop


Lecture 48 - Summary of Week 05


Lecture 49 - Introduction to Convolution Neural Networks (CNN)


Lecture 50 - Types of convolution


Lecture 51 - CNN Architecture Part 1 (LeNet and Alex Net)


Lecture 52 - CNN Architecture Part 2 (VGG Net)


Lecture 53 - CNN Architecture Part 3 (GoogleNet)


Lecture 54 - CNN Architecture Part 4 (ResNet)


Lecture 55 - CNN Architecture Part 5 (DenseNet)


Lecture 56 - Train Network for Image Classification


Lecture 57 - Semantic Segmentation


Lecture 58 - Hyperparameter optimization


Lecture 59 - Transfer Learning


Lecture 60 - Segmentation of Brain Tumors from MRI using Deep Learning


Lecture 61 - Activation Functions


Lecture 62 - Learning Rate decay, Weight initialization


Lecture 63 - Data Normalization


Lecture 64 - Batch Norm


Lecture 65 - Introduction to RNNs


Lecture 66 - Example - Sequence Classification


Lecture 67 - Training RNNs - Loss and BPTT


Lecture 68 - Vanishing Gradients and TBPTT


Lecture 69 - RNN Architectures


Lecture 70 - LSTM


Lecture 71 - Why LSTM Works


Lecture 72 - Deep RNNs and Bi- RNNs


Lecture 73 - Summary of RNNs


Lecture 74 - Introduction.


Lecture 75 - Knn


Lecture 76 - Binary decision trees


Lecture 77 - Binary regression trees


Lecture 78 - Bagging


Lecture 79 - Random Forest


Lecture 80 - Boosting


Lecture 81 - Gradient boosting


Lecture 82 - Unsupervised learning and Kmeans


Lecture 83 - Agglomerative clustering


Lecture 84 - Probability Distributions- Gaussian, Bernoulli


Lecture 85 - Covariance Matrix of Gaussian Distribution


Lecture 86 - Central Limit Theorem


Lecture 87 - Naïve Bayes


Lecture 88 - MLE Intro


Lecture 89 - PCA - Part 1


Lecture 90 - PCA - Part 2


Lecture 91 - Support Vector Machines


Lecture 92 - MLE, MAP and Bayesian Regression


Lecture 93 - Introduction to Generative model


Lecture 94 - Generative Adversarial Networks (GAN)


Lecture 95 - Variational Auto-encoders (VAE)


Lecture 96 - Applications: Cardiac MRI - Segmentation and Diagnosis


Lecture 97 - Applications: Cardiac MRI Analysis - Tensorflow code walkthrough


Lecture 98 - Introduction to Week 12


Lecture 99 - Application 1 description - Fin Heat Transfer


Lecture 100 - Application 1 solution


Lecture 101 - Application 2 description - Computational Fluid Dynamics


Lecture 102 - Application 2 solution


Lecture 103 - Application 3 description - Topology Optimization


Lecture 104 - Application 3 solution


Lecture 105 - Application 4 Solution of PDE/ODE using Neural Networks


Lecture 106 - Summary and road ahead