Objectives and competences
The objective of this course is to comprehensively present the knowledge about the development of intelligent systems with machine learning, and to train students for state-of-the-art machine learning approaches used in science and industry.
Content (Syllabus outline)
• Introduction: data science, artificial intelligence and machine learning, fields of use, software tools and frameworks.
• Intelligent information solutions: programming from scratch, integrated solutions for data scientists, machine learning as a service.
• Machine learning process: basic methods and tasks, data collection and processing, feature selection, transformation and feature creation, evaluation of knowledge models.
• Ensemble methods: combining machine learning methods, bagging, boosting, stacking, Random Forests, Gradient Boosting.
• Deep learning and neural networks, convolutional neural networks, recurrent neural networks, autoencoders, generative adversarial networks.
• Setting and optimization of machine learning parameters.
• Arranging machine learning projects.
• Case studies of efficient intelligent solutions from various domains.
Learning and teaching methods
• lectures,
• case studies,
• computer tutorials,
• project.
Intended learning outcomes - knowledge and understanding
Knowledge and understanding:
On completion of this course the student will be able to
• understand the applicability of various machine learning methods,
• choose and use the appropriate machine learning method and prepare the data to solve a given task,
• use ensemble methods and neural networks to solve real-world problems,
• properly set and optimize machine learning parameters,
• plan, perform and lead an intelligent solution development project,
• analyse and evaluate specific intelligent solutions and/or machine learning based systems.
Intended learning outcomes - transferable/key skills and other attributes
• Communication skills: writing the technical report.
• Use of information technology: use of program tools and environments for the development of intelligent machine learning solutions.
• Problem solving: systematic approach to problem solving with the use of intelligent methods, intelligent data analysis.
• Working in a group: participation in a project team.
Readings
• A. Géron: Hands-on Machine Learning with Scikit-Learn, Keras & TensorFlow – Concepts, Tools, and Techniques to Build Intelligent Systems, 2nd edition, O'Reilly Media, 2019.
• G. Bonaccorso, A. Fandango, R. Shanmugamani: Python: Advanced Guide to Artificial Intelligence – Expert machine learning systems and intelligent agents using Python, Packt Publishing, 2018.
• F. Chollet: Deep Learning with Python, Manning Publications, 2017.
• A. Thakur: Approaching (Almost) Any Machine Learning Problem, Abhishek Thakur, 2020.
• J. Hearty: Advanced Machine Learning with Python: Solve data science problems by mastering cutting-edge machine learning techniques in Python, Packt Publishing, 2016.
Additional information on implementation and assessment Midterm exams may be replaced by a written exam.