Goal
Upon successful completion of the course, the student will be able to:
- Recognize opportunities, limitations and possibilities of applying Artificial Intelligence techniques in various areas of modern life
- Point out the specificity of individual problems, the selection and adaptation to them of appropriate techniques
- Plan to evaluate alternative methods in comparison with each other to solve specific problems, recognizing the possibilities and limitations of each method/technique
- Communicate ideas related to the application of Artificial Intelligence techniques in a clean, clear and formal manner. The overall aim is students to design, build and evaluate Artificial Intelligence systems to solve real-world problems, and explain their operation
Also, the course targets to the following general competencies:
- Ability to organize and plan work and time management
- Ability to communicate effectively (orally and written)
- Ability to solve problems
- Ability to develop critical thinking and capacity for critical approaches
- Ability to work in a team
- Ability of interdisciplinary approaches
- Ability to apply theoretical knowledge in practice
- Ability to do research
- Ability to adapt methods and techniques to new situations and conditions
- Ability to generate new ideas – Creativity
Contents
- Applications of machine learning graph data (machine learning on graph data). Graph representation, feature engineering, community extraction from graphs
- Recommender systems: basic approaches and new outcome evaluation metrics
- Medical Information coding, standards, digital representation of biomedical signals and data
- Knowledge Representation in Biomedicine, Biomedical Systems with Context Aware Features, Biomedical Signal and Data Processing for Feature Extraction.
- Decision Support Systems in Biomedicine, Biomedical Image and Signal Analysis, Using Deep Learning for Medical Image Characterization, Case Studies
- Applications of Semantic Web technologies
- Automated software synthesis
- Applications of reinforcement learning and imitation learning in traffic management
- Explainability and interpretability of reinforcement learning methods in critical problems
- Artificial intelligence in the natural sciences
Bibliography
- Papadopoulos G. et al. Automating the Resolution of Flight Conflicts: Deep Reinforcement Learning in Service of Air Traffic Controllers. PAIS@ECAI 2022: 72-85
- Kravaris, T., Lentzos, K., Santipantakis, G. et al. Explaining deep reinforcement learning decisions in complex multiagent settings: towards enabling automation in air traffic flow management. Appl Intell 53, 4063–4098 (2023). https://doi.org/10.1007/s10489-022-03605-1
- Vouros G. Explainable Deep Reinforcement Learning: State of the Art and Challenges, 2022, ACM Comp. Surv. https://doi.org/10.1145/352744
- A. Blum, V. Kumar, A. Rudra, F. Wu. Online Learning for Online Auctions. Theoretical Computer Science 324: 137- 146 (2004).
- S. Arora, E. Hazan, S. Kale. The Multiplicative Weights Update Method: a Meta-Algorithm and Applications. Theory of Computing 8(6): 121 - 164 (2012)
- P. Auer, N. Cesa-Bianchi, Y. Freund, R. E. Schapire. The Nonstochastic Multiarmed Bandit Problem. SIAM Journal on Computing 32(1): 48– 77 (2002).
- Rajeev Alur, Rastislav Bodik, et al., “Syntax-Guided Synthesis”. 2013.
- Vijayaraghavan Murali, Letao Qi, Swarat Chaudhuri, Chris Jermaine, “Neural Sketch Learning for Conditional Program Generation”. arxiv:1703.05698
- Fei Wang, James Decker, et al. “Backpropagation with Callbacks: Foundations for Efficient and Expressive Differentiable Programming”. NIPS 2018.
- ime series analysis and modeling to Forecast, a survey, https://arxiv.org/pdf/2104.00164.pdf
- Jure Leskovec, Anand Rajaraman, Jeff Ullman. Mining of Massive Datasets. 2014, Cambridge University Press
- Optimization of Multi-stakeholder Recommender Systems for Diversity and Coverage, AIAI2021 (https://link.springer.com/chapter/10.1007/978-3-030-79150-6_55)
- Data mining for predicting gas diffusivity in zeolitic-imidazolate frameworks (ZIFs), DOI:10.1039/D2TA02624D
- A data-driven Bayesian optimisation framework for the design and stacking sequence selection of increased notched strength laminates, DOI: https://doi.org/10.1016/j.compositesb.2021.109347
- AI and Medicine by Mike Barlow Publisher(s): O'Reilly Media, Inc. ISBN: 9781492048954
- Machine Learning and AI for Healthcare Big Data for Improved Health Outcomes Authors: Panesar, Arjun APRESS ISBN 978-1-4842-3799-1
