IISc Bangalore · Computer Science
Mathematical Foundations for Machine Learning
Prof. Arulalan Rajan, Prof. Ashok Rao · 70 free video lectures
This course will provide a holistic approach to the mathematical foundations for Machine Learning. The course is focussed on developing mathematical ideas, necessary for machine learning applications, through intuitions and visualizations.The course primarily focuses on three important mathematical…
▶ Play on Open Lecture HallCourse page ↗
Lectures
- Why this course?
- Fields and Their Properties – Algebraic Tools for ML
- Fields, Vector Spaces
- Vector Spaces and Subspaces
- Combining Vectors and Linear Independence
- Basis and Dimension
- Linear Transformation - Intuition
- Subspaces associated with Linear Transformations
- Matrix representation of Linear Transformation
- Examples of Linear Transformation
- Eigenvalues and Eigenvectors
- Multiplicity of Eigen Values
- Diagonalization of Matrix
- Diagonalizability, Invariant subspaces
- Dot Product on Vector Space
- Orthogonality on Vector Space
- Orthonormal Basis
- Orthogonal Projections
- Construction of Orthogonal Basis
- Approximating a vector in any given subspace
- Real Symmetric Matrices
- Least Square Fitting and Pseudo Inverse - 1
- Least Square Fitting and Pseudo Inverse - 2
- Principal Component Analysis (PCA)
- Singular Value Decomposition (SVD)
- Singular Value Decomposition (SVD) Interpretation
- Support Vector Machine (SVM)
- Consolidating Week1 to Week 4
- Introduction to Probability - 1
- Introduction to Probability - 2
- Mutually Exclusive Events, Independent Events and Conditional Probability
- Total Probability Theorem and Bayes' Theorem
- Probability - A Measure Theoretic Insight
- Random Experiment and Random Variables
- Discrete Random Variables and Probability Mass Function (PMF)
- Types of Discrete Random Variables and Their Probability Distributions
- Continuous Random Variables
- Expected Value of Random Variable
- Moments and Variance
- Joint Distributions and Marginals
- Joint Moments of Random Variables
- Independence and Correlation
- Correlation and Covariance
- Joint Moments of Continuous random Variables and Conditioning of Random Variables
- Markov Inequality
- Chebychev Inequality
- Central Limit Theorem
- Sample Geometry
- Covariance Matrix & its properties
- Functions, Derivatives, Infinite Series
- Differentiation Rules
- Multivariate functions
- Gradient and Directional Derivatives
- Rules for Partial Derivatives, Jacobian and Hessian
- Matrix derivatives
- Optimization Overview
- Constrained Optimization, Optimal solutions, Saddle point
- Constrained optimization, Lagrange Multiplier
- Revisiting Least squares, Principal Component Analysis
- Minimizing the Cost Function: Gradent Descent Algorithm
- Variants of the Gradient Descent Algorithm
- Neural Networks , Perceptron
- Multilayer Layer Perceptron
- Back Propogation Algorithm
- Data and Patterns
- Classification and a simple binary classifier
- Classification, Clustering Techniques
- Linear Regression : Line of best fit
- Logistic Regression
- Course Summary, Credits & Acknowledgments
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