Applied Machine Learning – Fall 2023

Course No: 0907726
Course Name: Applied Machine Learning

Microsoft Team: Link

Handouts:
Course Syllabus (pdf)
Slides:

  • Course Introduction (pdf)
  • Python
  • Python Introduction (pdf)
  • Python Basics (pdf)
  • Important Python Packages (pdf)
  • Advanced Python (pdf)
  • NumPy (pdf)
  • ML
  • Machine Learning Introduction (pdf)
  • End-to-End Machine Learning Project (pdf)
  • Classification (pdf)
  • Information about the term project (pdf)
  • Training Models and Regression (pdf)
  • Classical Techniques (pdf)
  • Unsupervised Learning and Clustering (pdf)
  • Neural Networks (pdf)
  • Artificial Neural Networks with Keras (pdf)
  • Deep Neural Networks (pdf)
  • Deep Computer Vision Using Convolutional Neural Networks (pdf)
  • Recurrent Neural Networks (pdf)
  • Reinforcement Learning (pdf)
  • Recommender Systems (pdf)

Videos:

  • Lecture 1: Course Introduction and ML Introduction (Part 1, Part 2)
  • Lecture 2: ML Introduction (Slide 28 to 46) and Python (Link)
  • Lecture 3: Python Basics, Important Python Packages (Link)
  • Lecture 4: Important Python Packages, Advance Python (Part 1, Part 2)
  • Lecture 5: Chapter 2: End-to-End Machine Learning Project (Link)
  • Lecture 6: Chapter 2: End-to-End Machine Learning Project (Slides 26 to 58, Link), (Slides 59 to end, Link)
  • Lecture 7: Chapter 3 Classification (Slides 1 to 29, Link), (Slides 30 to end, Link)
  • Lecture 8: Chapter 4: Training Models and Regression (Link)
  • Lecture 9: Chapters 5, 6, & 7: Classical Techniques (Slides 1 to 25, Link), (Slides 26 to end, Link)
  • Lecture 10: Chapter 8 & 9: Unsupervised Learning and Clustering (Link)
  • Lecture 11: Chapter 10: Neural Networks (Link, until Minute 1:13), Artificial Neural Networks with Keras (Slides 1 to 23, Link), (Slides 24 to end, Link)
  • Lecture 12: Chapter 11: Training Deep Neural Networks (Link)
  • Lecture 13: Recurrent Neural Networks and Reinforcement Learning (Link)
  • Lecture 14: Recommender Systems (YouTube)

Lab Manual:

  1. Python Toolkits
  2. Basic Python Programming: Loops, Sets, Functions, and Classes
  3. Advanced Python Programming: Processing Text Files (uses file1.txt)
  4. NumPy Exercises
  5. Data Preparation and Regression (uses ‘diabetes.features.csv’ and ‘diabetes.labels.csv’)
  6. Regression with Simple Data Preparation (uses E6_Regression.csv)
  7. Classification with Moderate Data Preparation (uses leave.csv)
  8. Regression and Classification Using Classical Techniques
  9. Unsupervised Learning: Using PCA for Dimensionality Reduction (uses ‘Wholesale customers data.csv’)
  10. Regression and Classification Using Neural Networks
  11. Deep Neural Networks (uses DNN.ipynb)

Solutions:

  • Midterm Exam (pdf)

Grades: Are posted on MS Teams

Last update on 8/1/2024