Course Overview
The course introduces fundamental paradigms of artificial intelligence and machine learning with applications to intelligent data analysis in renewable energy systems. Students learn about knowledge representation, Bayesian networks, supervised and unsupervised learning, neural networks (including recurrent and convolutional architectures), decision trees, time series processing, and deep learning methods. Practical sessions cover data preparation, preprocessing, normalization, augmentation, model training, hyperparameter tuning, and performance evaluation. Emphasis is placed on applying AI/ML techniques to engineering and energy-related datasets, with implementation in Python and Jupyter notebooks.
MAIN GOAL
To provide students with theoretical foundations and practical skills in artificial intelligence and machine learning methods for intelligent data analysis, with applications in renewable energy systems.
Learning Outcomes
On completion of this module the learner will gain:
- + Ability to prepare, preprocess, and normalize engineering datasets.
- + Competence in selecting, training, and tuning machine learning models.
- + Understanding of supervised, unsupervised, and deep learning paradigms.
- + Skills in evaluating and presenting results of AI/ML models for engineering applications.
MEET YOUR INSTRUCTORS
Course Co-ordinator
Admissions
Entry Requirements
- + Basic programming in Python and familiarity with Jupyter notebooks.
Teaching and Assessment Methods
- + Lectures: 15h
- + Laboratories: 15h
- + Assessment: Assessment based on lab reports (50%) and written test (50%).
Application Deadline: Check institution page using link below
Fees & Funding
Tuition Fees
Visit institution page for information on fees and application deadlines.
Click here to visit institution page
Practical Notes
Contact Piotr Szczuko for any additional information relating to this course.
