Pattern Recognition & Machine Learning

This module provides a rigorous technical trajectory from classical statistical methods to advanced neural computing. It is designed to equip students with the ability to automate the categorization of complex entities through the construction of optimized Machine Learning (ML) pipelines.

Environment: Google Colab and/or Python (Anaconda & Jupyter Notebooks)

Participants who successfully complete the final assignment will be awarded a Certificate of Attendance by Neapolis University Pafos.

Course Availability: This course will be active during the Fall and Spring academic semesters of 2026–2027

Application deadlines:
Fall semester: 1 May - 30 September
Spring semester: 1 October - 31 January

Duration: 10 weeks

Course type: Online short course / Asynchronous learning through recorded lectures, readings, quizzes and self-paced activities

Assessment Breakdown:

Continuous Formative Assessment: 10% (Weekly quizzes/reflections).
Midterm Project: 20% (Data Prep & Linear Modeling).
Programming Assignments: 30% (3 Python projects).
Final Summative Exam: 40% (Comprehensive Theory & Logic).

Weekly Curricular Scope

Week	Lecture Title	Practical Lab Title
Wk 01	Lecture 01: Introduction to ML	Lab 01: Exploring Python for ML
Wk 02	Lecture 02: Data Preparation	Lab 02: Data Preparation in Python
Wk 03	Lecture 03: Regression Analysis	Lab 03: Binary Classification in Python
Wk 04	Lecture 04: Advanced Classification Techniques	Lab 04: Multi-class Classification in Python
Wk 05	Lecture 05: Ensemble Learning Methods	Lab 05: Ensemble Learning in Python
Wk 06	Lecture 06: Advanced Ensemble Methods	Lab 06: Advanced Boosting in Python
Wk 07	Lecture 07: Clustering and Segmentation	Lab 07: Cluster Analysis
Wk 08	Lecture 08: Patterns of Association	Lab 08: Association Rule Mining
Wk 09	Lecture 09: Introduction to ANN	Lab 09: Intro to ANN
Wk 10	Lecture 10: Deep FeedForward NN	Lab 10: Deep Learning

By the EOD of this module, students will be able to:

Build end-to-end ML pipelines including cleaning, feature engineering, and model selection.
Optimize supervised and unsupervised models using industry-standard libraries.
Apply advanced ensemble techniques (Bagging, Boosting, Stacking) to improve performance.
Design Deep FeedForward Neural Networks using backpropagation.
Evaluate model effectiveness via Accuracy, Precision, Recall, F1-Score, and ROC/AUC.

Participants who successfully attend the course will receive a Certificate of Attendance from Neapolis University Pafos.

Pattern Recognition & Machine Learning

Course content

Graduate profile