Lectures and Presentations I have delivered:

Arranged according to topics

Machine Learning & Convex Analysis: Video Lectures

Pls Note: Lectures involving Convex Analysis (Convex Optimization) of Machine Learning algorithms are explicitly named as "& Convex Analysis".
  1. Machine Learning: Linear Regression. Download-pdf.
  2. Machine Learning: Locally Weighted Regression
  3. Machine Learning: Logistic Regression.
  4. Machine Learning: Probabilistic Interpretation of Least-Squares. Download-pdf.
  5. Machine Learning: Exponential Family Distribution & Sufficient Statistics. Download-pdf.
  6. Machine Learning: Gaussian Discriminant Analysis
  7. Machine Learning: Non-Linear Regression
  8. Machine Learning: Linear & Least-Squares Discrimination and Robustness Issues. Download-pdf.
  9. Machine Learning: Agglomerative Hierarchical Clustering & Bayesian Information Criterion
  10. Machine Learning: Kullback-Leibler Divergence & Convex Analysis
  11. Machine Learning: Perceptron Learning & Kernel Perceptron. Download-pdf file
  12. Machine Learning: SVM & In-Depth Convex Analysis. Download-pdf-file.

Reinforcement Learning: Video Lectures

- My first 5 Lectures Explain first 6 Chapters of "Reinforcement Learning: An Introduction" -R. Sutton & A. Barto (1998).
  1. Reinforcement Learning: An Introduction to Reinforcement & Path Planning
  2. Reinforcement Learning: Value Functions & Markov Property
  3. Reinforcement Learning: Iterative Algorithms of Reinforcement Learning
  4. Reinforcement Learning: Monte Carlo Methods and Introduction to ECAN & RL application
  5. Reinforcement Learning: Temporal Difference Learning
  6. Reinforcement Learning: Least-Squares Temporal Difference Learning Download-pdf
  7. Reinforcement Learning: Fixed-Point Estimation of State-Action Value Function & Least-Squares Policy Iteration Download-pdf
  8. Reinforcement Learning: Geometric Analysis of Bellman Residual Minimization & Fixed Point Methods Download-pdf-file
  9. Reinforcement Learning: Kernelized Value Function Approximation Download-pdf-file

Convex Optimization Applications: Video Presentations

  1. Audio Reconstruction: An Optimization Approach
  2. Path Planning: Ellipsoidal Surfaces and Minimum Volume Ellipsoids Download-pdf
  3. Kullback-Leibler Divergence & Convex Analysis

Path Planning: Video Presentations

  1. Path Planning: Ellipsoidal Constrained Agent Navigation (My own algorithm) Download-pdf

Convex & Combinatorial Optimization: Video Lectures

  1. General Mathematical Optimization: Introduction. Download-pdf.
  2. Unconstrained Minimization: Theoretical Analysis of Stopping Criterion & Condition Number. Download-pdf.
  3. Unconstrained Minimization: Backtracking Line Search & Gradient Descent. Download-pdf.
  4. Unconstrained Minimization: Convergence Analysis of Gradient Descent using Line-Search. Download-pdf.
  5. Unconstrained Minimization: Steepest Descent Methods and Convergence Analysis Under Backtracking. Download-pdf.
  6. Unconstrained Minimization: Newton Method Using Backtracking Line Search. Video Lec - Coming Soon. Download-Pdf.

Mathematical Optimization: Lectures - (these will be removed in future)

  1. Mathematical Optimization: Introduction and General Overview - (in 3 parts, embedded from youtube): Part-1 Part-2 Part-3
  2. Mathematical Optimization: Line Search Methods - (in 3 parts, uploaded on youtube, and embedded in searching-eye): Part-1 Part-2 Part-3

Image Processing: Applications

  1. Image Processing: Hand Finger Detection Using Image Processing

My Course: ARL-10/11 :- Advanced Reinforcement Learning-2010/11.
CCO-10/11: Convex & Combinatorial Optimization-2010/11.
My CLTI: CFMAS: SP-11 :- Coalition Formation in Multi-Agent Systems: Strategic Planning-2011.
My Course: MLR :- Machine Learning Repertoire.
Return to Home Page
Return to Searching-Eye
ARL-10/11
CCO-10/11
MLR
CFMAS:SP-11
SSMS
Machine Learning Channel
Reinforcement Learning Channel

Following are coming soon:

These lectures would be more practical
  1. Decomposition Methods
  2. Averaging in Subgradient Methods for Optimization
  3. Steepest Descent Methods - Uploaded
  4. Newton′s Method
  5. Self-Concordance
  6. Network Flow: Linear Programming
  7. Support Vector Clustering
  8. Support Vector Regression
Except MILP, MIQP and Lower Bound Computation, if there is any special topic that you would like me to explain in Machine Learning, Reinforcement Learning or Convex Optimization channel of Searching-Eye, then please send mail to sanjeev.searchingeye@gmail.com