syllabus - Intro. to Machine learning

  • Course Description. Machine Learning (ML) is the design of a system that can learn from data. This course covers the basics of ML such as Supervised Learning, Unsupervised Learning, and Reinforcement Learning.
  • Coursework. Coursework will consist of weekly homework, quizzes , midterm, and a final exam. The overall grade will be determined %10 from class activity, 10% for each quiz, 10% from midterm, and 60% from the final exam.
  • Exam policy. No collaboration is permitted during the exam . If any collaboration with the intention of copying is caught, the student will get a failing grade.
  • Smartphone policy. Smartphones are not allowed during lectures.
  • Text. The course textbook is "Introduction to Machine Learning", Third Edition, by Ethem Alpaydin. As an additional text book: "Introduction to Machine Learning with Python" by Andreas C. Mueller and Sarah Guido,
  1. Week 1 - Introduction
    1. Why machine learning?
    2. A First Application: Classifying iris species
  2. Week 2 - Supervised Learning
    1. Classification and Regression
    2. Generalization, Overfitting and Underfitting
    3. Supervised Machine Learning Algorithms
    4. k-Nearest Neighbor
    5. Linear models
  3. Week 3 - Supervised Learning
    1. Naive Bayes Classifiers and Gaussian class-conditional distribution
    2. Decision trees and Ensembles of Decision Trees
    3. Kernelized Support Vector Machines
  4. Week 4 - Supervised Learning
    1. Logistic regression, gradient descent, Neural Networks (Deep Learning)
    2. Uncertainty estimates from classifiers
    3. Quiz 1
  5. Week 5 - Unsupervised Learning and Preprocessing
    1. Types of unsupervised learning
    2. Preprocessing and Scaling
  6. Week 6 - Unsupervised Learning and Preprocessing
    1. Dimensionality Reduction, Feature Extraction and Manifold Learning
    2. Advanced discussion on clustering and EM
  7. Week 7 - Representing Data and Engineering Features
    1. Categorical Variables
    2. Binning, Discretization, Linear Models and Trees
    3. Interactions and Polynomials
    4. Midterm
  8. Week 8 - Representing Data and Engineering Features
    1. Univariate Non-linear transformations
    2. Automatic Feature Selection
    3. Utilizing Expert Knowledge
  9. Week 9 - Model evaluation and improvement
    1. Cross-validation
    2. Grid Search
  10. Week 10 - Model evaluation and improvement
    1. Evaluation Metrics and scoring
    2. Using evaluation metrics in model selection
  11. Week 11 - Algorithm Chains and Pipelines
    1. Parameter Selection with Preprocessing
  12. Week 12 - Working with Text Data
    1. Types of data represented as strings
    2. Rescaling the data with TFIDF
    3. Topic Modeling and Document Clustering
    4. Quiz 2
  13. Reinforcement Learning
  14. Reinforcement Learning