In this repository, you will find code snippets and practical examples to build proficiency in various unsupervised machine-learning techniques. These resources help users grasp core concepts and apply them to real-world data. The topics covered include:
- Clustering: Techniques such as K-Means, Gaussian Mixture Models (GMMs), DBSCAN, and more.
- Dimensionality Reduction: Methods like Principal Component Analysis (PCA) and t-distributed Stochastic Neighbor Embedding (t-SNE) for simplifying complex data.
- Association Rules: Understanding relationships between variables within large datasets.
- Auto-Encoders: Implementing neural network-based models for data compression and anomaly detection.
All code is written in Python and organised into multiple Jupyter Notebooks for easy exploration and execution. The repository also includes a 'data' folder containing various datasets to facilitate hands-on learning as you run the provided notebooks.
Below is the unit outline with links to the study material:
| Week | Lectures | Practices & Activities | Resources & References |
|---|---|---|---|
| 9 - 15 Sep | - Introduction to U-ML (Slides - Video) | - NA | - Book 1 (Link) - Book 2 (Link) |
| 16 - 22 Sep | - K-Means (Notes) - K-Means, Part 1 (Video) - K-Means, Part 2 (Video) |
- K-Means Python from Scratch Notebook - K-Means Python from Scratch Notebook - K-Means Python; workout example (Video) |
- Resource - Resource - Resource |
| 23 - 29 Sep | - Hierarchical Clustering (Notes) - DBSCAN(Link) |
- Simple Hierarchical Clsutering; Python Notebook - Hierarchical Clsutering for Embedded Digits; Python Notebook |
- |
| - 30 - 6 Oct | - Principal Component Analysis, PCA, (Link) | - | - |
| - 7 - 13 Oct | - t-distributed Stochastic Neighbor Embedding, t-SNE, (Link) | - | - |