CS6140 / DS4420 Machine Learning Sec 3, SPRING 2019

(DS4420 has same syllabus, but lower assignments)

     About CS6140     Home     Schedule     Piazza     Final Project(optional)       VideoArchive       Grades

* Schedule and materials subject to change
Week / Module Topic / Lecture Other Reading Assignment
  • 1/7 - 1/14
  • Week 1 / Module 1: Intro, Decision Tree
  • Course Map

  • Topics:
  • Administrative
  • Intro to ML, Matrix Data
  • Rule-based Classifiers
  • Decision/Regression Trees
  • Linear Regression
  • HW 1
  • Due: Wed 1/23
  • 01/14 - 1/21
  • Topics:
  • Setup, Cross Validation
  • Error, Accuracy, ROC, AUC


Notes: Ridge Regression (normal equations)

  • DHS ch 5 (up to 5.4.2)
  • KMPP ch 7 (up to 7.5)



  • 1/21 - 1/28
  • Topics:
  • Gradient Descent
  • Linear Regression with GD
  • Logistic Regression
  • Newton Method


  • DHS ch 5
  • KMPP ch 7, 8
  • 1/28 - 2/6
  • Topics:
  • Perceptrons
  • Neural Networks


  • DHS ch 6
  • HW3
  • Due: Tue 2/19
  • 2/5 - 2/12
  • Topics:
  • Probabilities as data densities
  • Maximum Likelihood, fit params to data
  • Gaussian Discriminant Analysis
  • Naive Bayes
  • DHS ch 2, 3
  • KMPP ch 2, 3, 4
  • 2/12 - 2/19
  • Topics:
  • EM algorithm for fitting mixtures
  • Graphical Models
  • Notes: EM for Gaussian mixtures - Aron D'souza
  • Slides (1): EM
  • Slides (2): EM
  • Screencast

    • 2/19 - 2/26
    • Topics:
    • EM algorithm for fitting mixtures
    • Graphical Models
  • Optional: Graphical Models / factor graphs
  • Graphical models - Bishop slides

  • Smoothing
  • Slides (set 1): Other EM

    • 2/26 - 3/3
    • Topics:
    • Online Learning
    • Adaboost Algorithm
    • Bagging
    • RankBoost, Gradient Boosting


    • 3/3 - 3/10
    • SPRING BREAK
    NO CLASSES
    LIMITED OFFICE HOURS
    • 3/11 - 3/18
    • Topics:
    • Active Learning and VC Dimension
    • Multiclass ECOC



    • DHS ch 9.5
    • KMPP ch 16.6
    • KMPP ch 27.6.2

    • 3/18 - 3/25
    • Topics:
    • Margins, Boosting Feature Analysis
    • PCA and LDA, Lagrangian Multipliers
    • Missing Values

    • PCA: DHS ch 10
    • KMPP ch 25
    • HW 6
    • Due: Fri 3/27

    • Topics:
    • HAAR Features for Images
    • Regularized Regression RIDGE and LASSO
    • Text Features

    Stanford slides

    regularized Logistic Regression-Andrew Ng  (paperscreencast)

    Haar features integrated with  boosting




    • 3/25 - 4/1
    •  
    • Topics:
    • Support Vector Machines
    • Duality with KKT conditions
    • Maximizing Margins Constrained Optimization
    • SMO Algorithm



    • DSH ch 5.11
    • KMPP ch 14
    • 4/1 - 4/8
    • Topics:
    • Kernels
    • Kernels for SVM

    paper: Kernel Methods in Machine Learning



    • 4/8- 4/15
    •    
    • Topics:
    • Catching up
    • Recap
    • Extra Demo Days
    (prof Jay Aslam)




    • 4/15- 4/20

    • Week 14 / Module 7: Locality and Similarity
    • Course Map

    • Topics:
    • K-Nearest Neighbor
    • Kernel Similarity and KNN
    • Kernel Density Estimation
    • Heat Kernels, Harmonic Equation
    • Collaborative Filtering
    • KMPP ch 14, ch 1
    • DHS ch 4
    • Clustering: DHS ch 3.8, KMPP ch 12.2

    SAT 4/20 10AM - 4PM room WVH210 Final Exam Computer Required. Allowed: notes, books, internet access, etc. Not allowed: collaboration.