Machine Learning for Intelligent Systems

Recommended Prerequisites

Advanced Engineering Mathematics; Probability and Statistics; Programming.

Teaching Methods

Tutorial (OT) and Seminar (S) classes. Assessment: practical and research-oriented work with elaboration of a technical-scientific report and oral presentation. 

Learning Outcomes

After attending this course, students should have acquired the scientific and technical knowledge  necessary for understanding machine learning (ML), with focus on deep learning (DL) based methods, and their application in the context of  intelligent systems. This module will introduce and discuss advanced machine learning algorithms, DL techniques, and will present practical use-cases to engage the PhD student in active research. Applications include intelligent robots, intelligent vehicles (e.g., autonomous driving), cognitive systems, edge computing, intelligent mobile communications (e.g., for localization and tracking), smart/intelligent grids for efficient energy systems.

Work Placement(s)

No

Syllabus

Introduction to ML, DL and Intelligent Systems (IS). Machine Learning fundamentals and algorithms. Deep Learning principles and techniques. Convolutional Neural Networks. Sequential learning, Recurrent Neural Networks. Deep Reinforcement Learning. High-performance computing for training ML models. Advanced topics (e.g., probabilistic inference, explainability, interpretability, uncertainty quantification). Applications in IS (e.g., intelligent robotics, machine vision, advanced edge computing, smart grids).

Head Lecturer(s)

Cristiano Premebida

Assessment Methods

Assessment
Research work: 100.0%

Bibliography

1. Ian Goodfellow, Y. Bengio and A. Courville, “Deep Learning”, MIT Press 2016.

2. Christopher M. Bishop "Pattern Recognition and Machine Learning". Springer 2006.

3. A Géron, “Hands-on Machine Learning with Scikit-Learn and TensorFlow”, O'Reilly, 2017.

4. Murphy, K.P., “Probabilistic Machine Learning: An Introduction”, The MIT Press, 2021.

5. Magnus Ekman, “Learning Deep Learning: Theory and Practice of Neural Networks, Computer Vision, Natural Language Processing, and Transformers Using TensorFlow”, Addison Wesley Professional, 2021.

6. David Forsyth, “Applied Machine Learning”, Springer, 2019.

7. Shin, Y.C., Xu C., “Intelligent Systems, Modeling, Optimization, and Control”, CRC Press, 2009.

8. Sutton, R.S., Barto, A.G., “Reinforcement Learning: An Introduction”, 2nd Edition, The MIT Press, 2018.