Machine Learning for Beginners
An accessible introduction to machine learning concepts and Python tools, designed for African graduate students and early-career researchers.
Instructor: Dr. Yae Ulrich Gaba
Term: Workshop
Location: AIMS / AI.Technipreneurs
Time: Self-paced / Workshop sessions
Course Overview
This beginner-friendly course introduces the fundamental concepts of machine learning through hands-on Python notebooks. Designed for graduate students at AIMS and participants in Data Science Makers / AI.Technipreneurs workshops.
Participants will:
- Understand the core paradigms of machine learning
- Build and evaluate ML models using scikit-learn and PyTorch
- Apply clustering and dimensionality reduction techniques
- Get an introduction to geometric and topological approaches to ML
Prerequisites
- Basic Python programming
- High school mathematics (algebra, basic statistics)
Resources
- Course notebooks: AI.Technipreneurs GitHub
- Reference: The Shape of Data by Farrelly & Gaba
Schedule
| Week | Date | Topic | Materials |
|---|---|---|---|
| 1 | Session 1 | What is Machine Learning? Types of ML (supervised, unsupervised, reinforcement). The ML pipeline. | |
| 2 | Session 2 | Supervised Learning: Regression and Classification Linear regression, logistic regression, decision trees. Scikit-learn hands-on. | |
| 3 | Session 3 | Unsupervised Learning and Dimensionality Reduction K-means, PCA, t-SNE, UMAP. Clustering and visualization. | |
| 4 | Session 4 | Introduction to Neural Networks Perceptrons, backpropagation, PyTorch basics. From theory to code. | |
| 5 | Session 5 | Geometric and Topological ML Beyond Euclidean: graph neural networks, manifold learning, and TDA for ML. |