SYLLABUS - machine learning

Lectures: 102 16:00-20:00, Wednesday - 1st Sem.

  • Course Description. Machine Learning (ML) is the design of a system that can learn from data. This course covers the advanced topics of ML such as Data Preprocessing, Ensemble Learning, Parallelizing Neural Network Training with Theano, and Deep Belief Network.
  • 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 "Python Deeper Insights into Machine Learning", 1st Edition, by Sebastian Raschka, David Julian, John Hearty
  1. Week 1
    1. Giving Computers the Ability to Learn from Data
    2. Training Machine Learning Algorithms for Classification
  2. Week 2
    1. A Tour of Machine Learning Classifiers Using Scikit-learn
    2. Building Good Training Sets – Data Preprocessing
  3. Week 3
    1. Compressing Data via Dimensionality Reduction
    2. Learning Best Practices for Model Evaluation and Hyperparameter Tuning
  4. Week 4
    1. Combining Different Models for Ensemble Learning
    2. Applying Machine Learning to Sentiment Analysis
  5. Week 5
    1. Embedding a Machine Learning Model into a Web Application
    2. Predicting Continuous Target Variables with Regression Analysis
  6. Week 6
    1. Working with Unlabeled Data – Clustering Analysis
    2. Training Artificial Neural Networks for Image Recognition
  7. Week 7
    1. Parallelizing Neural Network Training with Theano
    2. Thinking in Machine Learning
  8. Week 8
    1. Tools and Techniques
    2. Turning Data into Information
  9. Week 9
    1. Models – Learning from Information
    2. Linear Models
  10. Week 10
    1. Neural Networks
    2. Features – How Algorithms See the World
  11. Week 11
    1. Learning with Ensembles
    2. Design Strategies and Case Studies
  12. Week 12
    1. Unsupervised Machine Learning
    2. Deep Belief Networks
  13. Week 13
    1. Stacked Denoising Autoencoders
    2. Convolutional Neural Networks
  14. Week 14
    1. Semi-Supervised Learning
    2. Text Feature Engineering
    3. Ensemble Methods
    4. Additional Python Machine Learning Tools