Introduction to Artificial Intelligence and Machine Learning

Course Objectives

• Understand what Artificial Intelligence and Machine Learning are, and how they are used in real-world contexts.
• Learn to work with data sets and prepare data for basic AI/ML models.
• Explore key machine learning concepts such as classification, regression, training, testing and evaluation.
• Write and run simple Python scripts to create, train and test basic machine learning models.
• Develop a small, functional AI-based application using the skills acquired during the course.

Schedule

Module 1 – Introduction to AI and Machine Learning

• What is Artificial Intelligence?
• What is Machine Learning and how is it different from traditional programming?
• Types of Machine Learning: supervised, unsupervised, reinforcement learning (basic overview)
• Real-world applications of AI/ML in different fields (health, finance, education, industry, etc.)
• Key concepts: model, algorithm, data set, features, labels, training and testing
• Introduction to the workflow of an ML project

Module 2 – Introduction to Python for AI

• Overview of the Python programming environment
• Using notebooks (Jupyter or Google Colab) for data science
• Variables, data types, lists, and dictionaries in Python
• Conditional statements and loops
• Functions and modular code basics
• Importing and using external libraries (pandas, numpy, matplotlib, scikit-learn)

Module 3 – Working with Data

• Loading and exploring structured data (CSV files) using pandas
• Understanding data frames, columns, rows, indexing and filtering
• Cleaning and preparing data: handling missing values, type conversion
• Feature selection and basic visualisation (matplotlib, pandas.plot)
• Splitting data into training and testing sets

Module 4 – Building Your First ML Model

• Understanding supervised learning
• Introduction to classification and regression
• Training a model with scikit-learn: fit() and predict()
• Simple algorithms: k-Nearest Neighbors, Linear Regression
• Making predictions and interpreting basic outputs
• Common challenges: overfitting and underfitting

Module 5 – Evaluating Model Performance

• Key metrics: accuracy, precision, recall, F1 score
• Confusion matrix: reading and interpreting results
• Cross-validation basics
• Visualising results with graphs and plots
• Adjusting model parameters (intro to hyperparameter tuning)

Module 6 – Unsupervised Learning and Clustering

• What is unsupervised learning?
• Introduction to clustering algorithms: K-Means
• Practical use cases: grouping data without labels
• Visualising clusters and understanding results
• Limitations and interpretation of clustering models

Module 7 – Final Project: Building a Simple AI Solution

• Project definition: choose a small dataset and define a problem to solve
• Preparing and cleaning the data set
• Selecting and training a model
• Evaluating performance and adjusting
• Presenting results with plots and explanations
• Group or individual project presentation and reflection