• See the Timetable for times and locations of classes and labs.
• Access to lecture and tutorial recordings can be found here on VStream or through Nuku shortly after each class.

Lecture Notes 2024

Week 1: Introduction and Overview

• Course Introduction: PDF
• Machine Learning Overview: PDF PPTX
• Machine Learning Tasks: machine_learning_task.pdf
• Tutorial: Python programming fundamentals:
  • Tutorial slides: basic_python_programming_tutorial.pdf
  • Tutorial examples (Jupyter notebook): AIML231_Week1_Tutorial.ipynb
  • Tutorial dataset: banknote.csv

Week 2: Supervised Learning (1) - Basic and Classification algorithms

• Lecture notes: Classification_technology_Part_1.pdf
• Classification models and algorithms, KNN, Training and Test
• Popular classifiers, Overfitting and Underfitting, Bias-Variance trade-off, Cross-Validation
• Tutorial: Use SKLearn library for classification: AIML231_Week2_Tutorial.ipynb

Week 3: Supervised Learning (2) - Classification Algorithms and Metrics

• Lecture notes: classification_technology_Part_2.pdf
• Popular classifiers, SVM, Classification Performance Metrics (1)
• Classification Performance Metrics (2) and Decision Tree

Week 4: Pipeline and Data Understanding

• Machine learning pipeline: Introduction, Construction of ML Pipeline and Case Study ML_Pipeline.pdf
• Exploratory Data Analysis, Visualisation W4_EDA.pdf
• EDA Tutorial using pandas, matplotlib, seaborn Tutorial code

Week 5: Data Preparation(1)

• Data Preprocessing W5_DataPreprocessing.pdf
• Feature Selection W5_FeatureSelection.pdf W5_FeatureSelection_dense.pdf
• Tutorial - Good Friday:
  • Recorded Tutorial Password: ?q3bEPy6
  • Tutorial code code
  • Sequential forward selection Example pdf

---

Mid-Trimester Teaching Break

---

Week 6: Data Preparation (2) and Regression

• Feature Construction W6_FeatureConstruction.pdf W6_FeatureConstruction_Dense.pdf
• Regression: Linear Regression and Regression Metrics W6_Regression.pdf W6_Regression_Dense.pdf
• Tutorial Tutorial code

Week 7: Unsupervised Learning and Reinforcement Learning

• (Tuesday) Unsupervised Learning: Clustering, K-Means Clustering and Hierarchical Clustering Techniques, and Clustering Metrics W7_Clustering.pdf
• (Friday) Reinforcement Learning: reinforcement_learning.pdf
• Tutorial: (to be provided as a recording)
  • Clustering tutorials: Notebook code Video Link Passsword: W1=TNRb0
  • Tutorial on Q-learning (you don't need to study this tutorial for any assignment or for the final test; this tutorial is just for your reference): video link
  • Example Python program for the Q-learning tutorial: q_learning.py.txt
• Python programming fundamental lab: Python_programming_lab.ipynb

Week 8: Neural Networks (1)

• Introduction to Neural Networks: PDF PPT
• Training Neural Networks: PDF PPT
• Tutorial AIML231-Week8-Tutorial.ipynb

Week 9: Neural Networks (2)

• Backpropagation: PDF PPT
• Automatic Differentiation: PDF PPT
• Tutorial AIML231 Week9-Tutorial.ipynb

Week 10: Search and Evolutionary Computation

• Search Methods: PDF PPT
• Evolutionary Computation: Genetic Algorithm: PDF PPT
• Tutorial AIML231-Week 10 Tutorial.pptx

Week 11: Advanced Topics (1)

• Advanced Regression and Clustering Techniques: PDF PPT
• Broader fields of machine learning, explainable AI (XAI), Ethical Considerations and Bias in Machine Learning
• Tutorial

Week 12: Advanced Topics (2) and Course Review

• AutoML: AutoML Theories, Techniques and Tools
• Course Review