IIT Madras · Computer Science

Machine Learning for Engineering and Science Applications

Prof. Balaji Srinivasan, Prof. Ganapathy · 107 free video lectures

107 video lectures. Topics: Introduction to the Course History of Artificial Intelligence; Overview of Machine Learning; Why Linear Algebra ? Scalars, Vectors, Tensors; Basic Operations; Norms; Linear Combinations Span Linear Independence; Matrix Operations Special Matrices Matrix Decompositions…

▶ Play on Open Lecture HallCourse page ↗

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
  5. Norms
  6. Linear Combinations Span Linear Independence
  7. Matrix Operations Special Matrices Matrix Decompositions
  8. Introduction to Probability Theory Discrete and Continuous Random Variables
  9. Conditional, Joint, Marginal Probabilities Sum Rule and Product Rule Bayes' Theorem
  10. Bayes' Theorem - Simple Examples
  11. Independence Conditional Independence Chain Rule Of Probability
  12. Expectation
  13. Variance Covariance
  14. Some Relations for Expectation and Covariance (Slightly Advanced)
  15. Machine Representation of Numbers, Overflow, Underflow, Condition Number
  16. Derivatives,Gradient,Hessian,Jacobian,Taylor Series
  17. Matrix Calculus (Slightly Advanced)
  18. Optimization - 1 Unconstrained Optimization
  19. Introduction to Constrained Optimization
  20. Introduction to Numerical Optimization Gradient Descent - 1
  21. Gradient Descent - 2 Proof of Steepest Descent Numerical Gradient Calculation Stopping Criteria
  22. Introduction to Packages
  23. The Learning Paradigm
  24. A Linear Regression Example
  25. Linear Regression Least Squares Gradient Descent
  26. Coding Linear Regression
  27. Generalized Function for Linear Regression
  28. Goodness of Fit
  29. Bias-Variance Trade Off
  30. Gradient Descent Algorithms
  31. Introduction to Week 5 (Deep Learning)
  32. Logistic Regression
  33. Binary Entropy cost function
  34. OR Gate Via Classification
  35. NOR, AND, NAND Gates
  36. XOR Gate
  37. Differentiating the sigmoid
  38. Gradient of logistic regression
  39. Code for Logistic Regression
  40. Multinomial Classification- Introduction
  41. Multinomial Classification - One Hot Vector
  42. Multinomial Classification - Softmax
  43. Schematic of multinomial logistic regression
  44. Biological neuron
  45. Structure of an Artificial Neuron
  46. Feedforward Neural Network
  47. Introduction to back prop
  48. Summary of Week 05
  49. Introduction to Convolution Neural Networks (CNN)
  50. Types of convolution
  51. CNN Architecture Part 1 (LeNet and 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
  58. Hyperparameter optimization
  59. Transfer Learning
  60. Segmentation of Brain Tumors from MRI using Deep Learning
  61. Activation Functions
  62. Learning Rate decay, Weight initialization
  63. Data Normalization
  64. Batch Norm
  65. Introduction to RNNs
  66. Example - Sequence Classification
  67. Training RNNs - Loss and BPTT
  68. Vanishing Gradients and TBPTT
  69. RNN Architectures
  70. LSTM
  71. Why LSTM Works
  72. Deep RNNs and Bi- RNNs
  73. Summary of RNNs
  74. Introduction.
  75. Knn
  76. Binary decision trees
  77. Binary regression trees
  78. Bagging
  79. Random Forest
  80. Boosting
  81. Gradient boosting
  82. Unsupervised learning & Kmeans
  83. Agglomerative clustering
  84. Probability Distributions- Gaussian, Bernoulli
  85. Covariance Matrix of Gaussian Distribution
  86. Central Limit Theorem
  87. Naïve Bayes
  88. MLE Intro
  89. PCA-part 1
  90. PCA-part 2
  91. Support Vector Machines
  92. MLE, MAP and 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 - Tensorflow code walkthrough
  98. Introduction to Week 12
  99. Application 1 description - Fin Heat Transfer
  100. Application 1 solution
  101. Application 2 description - Computational Fluid Dynamics
  102. Application 2 solution
  103. Application 3 description - Topology Optimization
  104. Application 3 solution
  105. Application 4 - Solution of PDE/ODE using Neural Networks
  106. Summary and road ahead
  107. Live Session 30-08-2019

From NPTEL (IITs and IISc) · CC BY-NC-SA. More from IIT Madras.

Open Lecture Hall is free, with no ads and no sign-up. It is not run by or connected to any university; the lectures are the universities' own free recordings, played from where they host them. About & rights