University laboratory notebooks covering core topics in machine learning, probabilistic modelling, and AI fundamentals, implemented in Python using Jupyter Notebooks.
This repository contains a series of laboratory exercises completed as part of a university-level module in Machine Learning and Artificial Intelligence.
Each lab is implemented as a Jupyter Notebook and focuses on both theoretical understanding and practical implementation using Python.
The labs progressively build knowledge across core ML and AI concepts, combining mathematical foundations with hands-on experimentation.
Lab1_20019971.ipynb Lab2_20019971.ipynb Lab3_20019971.ipynb Lab4_20019971.ipynb Lab5_20019971.ipynb Lab6_20019971.ipynb Lab7_20019971.ipynb Lab8_20019971.ipynb Lab9_20019971.ipynb Lab10_20019971.ipynb
Each notebook is self-contained and includes explanations, code, and outputs.
The labs cover topics such as:
- Python fundamentals for data analysis
- Probability and statistics for machine learning
- Data preprocessing and feature handling
- Supervised learning algorithms
- Model evaluation and performance metrics
- Regression and classification techniques
- Overfitting, bias–variance trade-offs, and regularisation
- Introduction to more advanced AI / ML concepts
(Exact content varies per lab and follows the module’s weekly structure.)
- Python 3
- Jupyter Notebook
- NumPy
- Pandas
- Matplotlib / Seaborn
- scikit-learn (where applicable)
Academic Context
These labs were completed as part of a university coursework module and are intended for educational and demonstration purposes. They reflect individual work and understanding developed throughout the course.
Author
Adesh Maharaj BEng Electronic & Computer Engineering MSc AI & Machine Learning University of Limerick