IISc Bangalore · Computer Science

Machine Learning for Core Engineering Disciplines

Prof. Ananth Govind Rajan · 65 free video lectures

This course will introduce students and practitioners of core engineering disciplines to the fundamentals and applications of machine learning. The course will cover the following material: introduction to data science and machine learning, examples of supervised/unsupervised/reinforcement…

▶ Play on Open Lecture HallCourse page ↗

Lectures

  1. Introduction to Data Science, Artificial Intelligence, and Machine Learning
  2. Fundamentals of Machine Learning
  3. Probability and Statistical Foundations for Machine Learning - I
  4. Probability and Statistical Foundations for Machine Learning - II
  5. Probability Distributions for Discrete and Continuous Random Variables
  6. Transforming Random Variables and Their Distributions
  7. Understanding Population and Sample Statistics - I
  8. Understanding Population and Sample Statistics - II
  9. Multivariate Linear Regression and Model Evaluation
  10. Hypothesis Testing and Confidence Intervals: Z-Test and T-Test
  11. Overfitting, Underfitting, and Ridge Regression
  12. LASSO and Elastic Net Regularization Techniques
  13. Bias-Variance TradeOff in Machine Learning
  14. Logistic Regression and Evaluation of Binary Classification Models
  15. ROC Analysis and Multiclass Classification
  16. Tutorial - I (Introduction to Python)
  17. Loss Functions - I
  18. Loss Functions - II
  19. Loss Functions - III
  20. Loss Function - IV
  21. Training ML Models: Gradient Descent
  22. Training ML Models: Gradient Descent and Hessian Matrix Analysis
  23. Practical Aspects of ML Model Training and Stochastic Gradient Descent
  24. Variants of Stochastic Gradient Descent for ML Model Training
  25. Gradient Descent Applied to Toy Quadratic Regression
  26. Cross Validation in Machine Learning
  27. Hyperparameter Tuning for ML Models
  28. Tutorial - II (Linear Regression using Python)
  29. Tutorial - III (Ridge and LASSO Regression, Cross Validation and Hyperparameter tuning using Python)
  30. Unsupervised Learning: Principal Component Analysis (PCA)
  31. Singular Value Decomposition and PCA
  32. Fundamentals of Clustering with K-means
  33. Advanced Clustering Techniques
  34. Nonlinear Dimensionality Reduction Techniques -I
  35. Nonlinear Dimensionality Reduction Techniques -II
  36. Unsupervised Learning on Toy Datasets
  37. Decision Trees in Supervised ML
  38. Decision Trees for Regression and Classification
  39. Classification using Simple Decision Trees
  40. Ensemble Learning
  41. Random Forest and Boosting of Decision Trees
  42. Adaptive Boosting (AdaBoost)
  43. Unsupervised Learning in Python (Tutorial 1)
  44. Unsupervised Learning in Python (Tutorial 2)
  45. Gradient Boosted Decision Trees and Advanced Boosting Libraries
  46. Decision Stump
  47. Support Vector Machines (SVM)
  48. Mathematics of SVM Margins
  49. Support Vector Regression (SVR)
  50. Kernel Ridge Regression (KRR)
  51. Gaussian Process Regression (GPR)
  52. Supervised Machine Learning Tutorial with Python (Tutorial I)
  53. Supervised Machine Learning Tutorial with Python (Tutorial II)
  54. Supervised Machine Learning Tutorial with Python (Tutorial III)
  55. Introduction to Deep Learning and Neural Networks
  56. Overview of Advanced Neural Network Architectures: From CNNs to GANs and GNNs
  57. Mathematical Foundation and Activation Functions of Neural Networks
  58. Training an Artificial Neural Network: Forward Propagation, Backpropagation, and Hyperparameters
  59. Challenges in Training Neural Networks and their Mitigation
  60. Neural Network Challenges (Gradients, Overfitting) and Logic Gate Implementation
  61. Recurrent Neural Networks and Sequential Data Processing
  62. Graph Neural Networks and Generative AI Fundamentals
  63. Variational Autoencoders and Bayesian Generative Modeling
  64. Neural Networks with Tensorflow (Tutorial I)
  65. Neural Networks with Tensorflow (Tutorial II)

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

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