Note: 1 ECTS = 25 to 30 h students workload; 1 h = 15 academic hours per semester,
UG=Undergraduate, G=Graduate, PG=Postgraduate


Seminar Explainable AI 2019

This course consists of 10 modules: Module 0 is voluntary and for students who need a refresher on probability and measuring information; Module 9 is mandatory, which is on “Ethical, Legal and Social Issues of Explainable AI”, where we deal with bias, fairness and trust of machine learning; the remaining Modules 1 to 8 are adaptable to the indiviual needs and requirements of the class and deal mainly with methodological aspects of explainable AI and interpretable AI in a research-based teaching style; we speak Python and experiments will be done with the Kandinsky-Patterns, our “Swiss-Knife” for the study of explainable ai (watch this video to get an idea). [Syllabus xAI 2019, pdf, 85kB]
Course Hompage: https://human-centered.ai/seminar-explainable-ai-2019/
GitHub page: https://github.com/human-centered-ai-lab/cla-Seminar-explainable-AI-2019


ECML-PKDD Tutorial 2019: From interactive Machine Learning to Explainable AI

In this  tutorial we learn some methodological basics on “explainable/interpretable AI” towards “ethical responsible machine learning”. We will explore the necessity to go “beyond explainable AI” towards causability measures which we need to design, develop, test and evaluate future Human‐AI dialog systems. Finally we will work with an open explanation environment [1]  the so‐called #KandinskyPatterns, which can als used as an IQ‐Test for machines. Slides (pdf, 5,112 kB) here:
[HOLZINGER-Part-2-From Interactive ML to explainable AI-ECML-PKDD]
[1] Project Homepage: https://human‐centered.ai/project/kandinsky‐patterns


185.A83 Machine Learning for Health Informatics (class of 2019) Start: 12th March 2019 (3 ECTS, 2 h, G)

In this course we cover some current topics of data driven AI/machine learning for medicine with a focus on explainable-AI (xAI). We follow a human-centered AI approach and integrate ethical, legal, psychological and sociological issues for the design of interpretable verifiable algorithms. The goal is to enable human domain experts (e.g. medical doctors) to understand the underlying explanatory factors (causality) of why an AI-decision has been made, paving the way for ethical responsible AI and transparent verifiable machine learning for decision support. [Syllabus, pdf, 77 kB]

Course homepage: https://human-centered.ai/machine-learning-for-health-informatics-class-2019


706.315 Selected Topics on interactive Knowledge Discovery: From explainable AI to causability (class of 2019, for PhDs only, 2 h PG)
This course is an extension of the last years “Methods of explainable AI”, which was a natural offspring of the interactive Machine Learning (iML) courses  (glass-box approaches) and the decision support courses held over the last years. Today the most successful AI/machine learning models, e.g. deep learning (see the difference AI-ML-DL) are often considered to be “black-boxes” making it difficult to understand the results, to re-enact on demand, to verify the plausibility of results and to answer the question of why a certain machine decision has been reached. This is an important step towards fairness in machine learning, understanding, reducing and avoiding bias.

706.046 AK HCI - Intelligent User Interfaces - Towards explainable-AI (class 2019) Start: 11th March 2019 (5 ECTS, 5 h, G)
706.046 AK HCI - Intelligent User Interfaces - Towards explainable-AI (class 2019) Start: 11th March 2019 (5 ECTS, 5 h, G)

Explainable-AI is of increasing importance for society, science and industry. Prestigious academic and commercial institutions (Google, Carnegie-Mellon, MIT, see here)  emphasize the importance of effective and efficient Human-AI interfaces to make AI/ML (see definition) approaches re-traceable, transparent, verifiable, and understandable, thereby explainable on demand. This calls for contextual adaptive dialogue systems (called “Explanation-Interfaces”), where human understandable natural language (NLP) plays a central role.

Course Homepage: https://human-centered.ai/intelligent-user-interfaces-2019/


706.998/706.999 DiplomandInnen/DissertantInnen Seminar (class of 2019, 3 ECTS, 2h UG, G)
706.998/706.999 DiplomandInnen/DissertantInnen Seminar (class of 2019, 3 ECTS, 2h UG, G)

For master and doctoral students of the Holzinger group; the seminar is compulsory, the aim is to help the master/doctoral candidates to improve their research work strategies and their communication and presentation abilities within their scientific field,  a particular focus is given on ethical, social and privacy aspects of human-centered ai, discussing not only current trends and successes but also potential issues of fairness and trust.

Course Homepage: https://human-centered.ai/scientific-working-for-students


Mini-Course: From Data Science to interpretable AI (class of 2019)

This Mini course is an introduction into decision making and on how human intelligence can be supported by Artificial Intelligence (AI) and data driven Machine Learning (ML) for efficient decision support systems. A special focus is given on interpretable AI and verifiable ethical-responsible machine learning due to its increasing importance for the health domain. Transparency, fairness and avoiding bias are very important issues – not only in medical AI. [Syllabus, pdf, 74 kB]

Course homepage: https://human-centered.ai/mini-course-interpretable-ai-class-of-2019/


706.315 Selected Topics on interactive Knowledge Discovery: Methods of explainable AI (for PhDs only, 2 h PG)
706.315 Selected Topics on interactive Knowledge Discovery: Methods of explainable AI (for PhDs only, 2 h PG)

The need for Explainability is motivated by lacking transparency of black-box machine learning (e.g. deep learning), particularly in the medical domain, which do not foster trust/acceptance of AI. Rising legal and privacy aspects (European GDPR, May, 28, 2018) will make black-box approaches difficult to use in future Business (see explainable AI), due to the (juridical) right for explanation. Other topics of explainable AI include the correlation fallacy and all sorts of biases, e.g. bias in interpretation, to ensure fairness of machine learning algorithms.

Course Homepage: https://human-centered.ai/methods-of-explainable-ai


185.A83 Machine Learning for Health Informatics (class of 2018) Start: 6th March 2018 (3 ECTS, 2 h, G)
185.A83 Machine Learning for Health Informatics (class of 2018) Start: 6th March 2018 (3 ECTS, 2 h, G)

We foster a research-based teaching (RBT) approach on current topics of AI/machine learning for the application in health informatics. Due to the importance, a special focus is this year given on explainable-AI and ethical, social, public issues of Artificial Intelligence for solving real-world problems in the medical domain.

Course homepage: https://human-centered.ai/machine-learning-for-health-informatics-class-2018/


Mini-Course MAKE-Decisions: From Data Science to Explainable-AI (class of 2018, 3 ECTS, 2h, PG)
Mini-Course MAKE-Decisions: From Data Science to Explainable-AI (class of 2018, 3 ECTS, 2h, PG)

This Course is an introduction into a core area of health informatics and helps to understand decision making generally and how human intelligence can be supported by Artificial Intelligence (AI) and Machine Learning (ML) (-> What is the difference between AI/ML?) with decision support systems, having a focus on ethical, social and legal aspects.

Course homepage: https://human-centered.ai/mini-course-make-decisions-practice/


706.046 AK HCI - Intelligent User Interfaces - Towards explainable-AI (class 2018) Start: 5th March 2018 (4,5 ECTS, 5 h, G)

Explainable-AI (xAI) is of increasing importance due to legal aspects (GDPR), but also for ethical and social aspects. The goal is to make AI/ML (see definition) approaches re-traceable, transparent, understanable and  thus explainable to a human. Ideally we make use of cognitive capabilities of a human-in-the-loop in a glass-box approach. This needs new concepts of explainable IUI’s particularly for ethical responsible data driven machine learning.

Course Homepage: https://hci-kdd.org/iui-explainable-ai

 


340.300 Principles of Interaction: Interaction with Agents and Federated ML (class of 2017, 3 ECTS, 2 h, G)

In this course Linz University computer science and software engineering students get to know the latest insights into collaborative interactive machine learning approaches, interaction with multi-agents and the human-in-the-loop with a focus on federated machine learning approaches.

Course Homepage: https://human-centered.ai/interactive-machine-learning/

 

 


MAKE-Health: Machine Learning & Knowledge Extraction for Health Informatics (class of 2017, 6 ECTS, 3 h, G)

This course at the University of Verona follows a research-based teaching (RBT) approach and discusses experimental methods for combining human intelligence with artificial intelligence with a strong focus on decision support systems and explainability. This course also considers ethical, social and legal aspects of human-centered ai, e.g. evaluating fairness and inclusion.

Course Homepage: https://human-centered.ai/mini-make-machine-learning-knowledge-extraction-health/

 


185.A83 Machine Learning for Health Informatics (class of 2017, 3 ECTS, 2h, G)
This course considers the whole pipeline from data preprocessing to data visualization and fosters the HCI-KDD approach, which encompasses a synergistic combination of methods from two areas to understand intelligence: Human-Computer Interaction (HCI) and Knowledge Discovery/Data Mining (KDD), with the goal of supporting human intelligence with artificial intelligence. A particualr focus is on ethical responsible machine learning and social aspects of ai in medicine.

706.046 AK HCI - Intelligent User Interfaces IUI (class of 2017, 4,5 ECTS, 5 h, G)

Intelligent User Interfaces (IUI) is where HCI meet the possibilities of Artificial Intelligence (AI), often defined as the design of intelligent agents – the core essence in Machine Learning. In this course, Software Engineering is seen as dynamic, interactive and cooperative process which facilitate an optimal mix of standardization and tailor-made solutions. For experimental issues gamification approaches are very useful. Putting the human-in-the-loop is the main focus of this course.

Course Homepage: https://human-centered.ai/iui-where-hci-meets-ai-challenge-2017/


706.315 Interactive Machine Learning - iML (class of 2016, 2 h PG)

This graduate course follows a research-based teaching (RBT) approach and provides an overview of models of human-centered ai and discusses methods for combining human intelligence with machine intelligence (human-in-the-loop). The application focus is on the health informatics domain, but the principles are useful in any business domain.

Course homepage for 2015 and 2016: https://human-centered.ai/lv-706-315-interactive-machine-learning/


709.049 Biomedical Informatics: discovering knowledge in (big) data (2010-2017, 3 ECTS, 2, UG)

This course covers computer science aspects of biomedical informatics (= medical informatics + bioinformatics).  The focus is on machine learning for knowledge discovery from data, and concentrates on algorithmic and methodological issues of data science. Health Informatics is the field where machine learning has the greatest potential to provide benefits in improved medical diagnoses, disease analyses, decision making and drug developments with high real-world economic value, ultimately contributing to cancer research for the human good. Ethical and social issues are very important aspects!

Course homepage (2010 – 2017): https://human-centered.ai/biomedical-informatics-big-data/


185.A83 Machine Learning for Health Informatics (class of 2016, 3 ECTS, 2 h, G)
185.A83 Machine Learning for Health Informatics (class of 2016, 3 ECTS, 2 h, G)

Machine Learning is the most growing field in computer science (Jordan & Mitchell, 2015. Machine learning: Trends, perspectives, and prospects. Science, 349, (6245), 255-260), and it is well accepted that Health Informatics is amongst the greatest challenges (LeCun, Bengio, & Hinton, 2015. Deep learning. Nature, 521, (7553), 436-444). For the successful application of Machine Learning in Health Informatics a comprehensive understanding of the whole HCI-KDD-pipeline, ranging from the physical data ecosystem to the understanding of the end-user in the problem domain is necessary. In the medical world the inclusion of privacy, data protection, safety and security is mandatory. Keywords: Automatic machine learning, interactive machine learning, doctor-in-the-loop, subspace clustering, protein folding, k-Anonymization Go to the Course Homepage


706.315 Interactive Machine Learning (class of 2015, 2 h PG)
706.315 Interactive Machine Learning (class of 2015, 2 h PG)

Whilst in classic ML usually there is little or no end users’ feedback (a Google car is intended to go without human-in-the-loop), iML takes the human-into-the-loop, hence let the end users’ control the learning behaviour: putting the huge potential of modern sophisticated machine learning algorithms into the hands of domain experts – so that the machine can benefit from the knowledge of this experts. Keywords: Interactive Learning and Optimization with the Human in the Loop, Hybrid Learning Systems, Active Learning, Active preference learning, reinforcement learning, Go to the Course Homepage


706.046 AK HCI - Intelligent User Interfaces - HCI meets AI (class of 2016, 4,5 ECTS, 5 h, G)
706.046 AK HCI - Intelligent User Interfaces - HCI meets AI (class of 2016, 4,5 ECTS, 5 h, G)

Intelligent User Interfaces (IUI) is where the Human-computer interaction (HCI) aspects meet Artificial Intelligence (AI), often defined as the design of intelligent agents – the core essence in Machine Learning. In this practically oriented course, Software Engineering is seen as dynamic, interactive and cooperative process which facilitate an optimal mixture of standardization and tailor-made solutions. Keywords: Experimental Software Engineering, Intelligent User Interfaces, Artificial Intelligence, Machine Learning Go to Course Hompeage


709.049 Medical Informatics / Medizinische Informatik (2010-2015)
709.049 Medical Informatics / Medizinische Informatik (2010-2015)

This course covers computer science aspects of biomedical informatics (= medical informatics + bioinformatics) with a focus on discovering knowledge from big data  concentrating on algorithmic and methodological issues. Medicine and Biology are turning more and more into a data science, consequently the focus of this lecture is on interactive knowledge discovery/data mining and interactive machine learning. Keywords: Biomedical Informatics, Data, Information, Knowledge Go to the course homepage Previous lecture slides from the last semester are available via: http://genome.tugraz.at/medical_informatics.shtml


706.318 DissertantInnenseminar - Ph.D. Seminar (every year 1 h, PG)
706.318 DissertantInnenseminar - Ph.D. Seminar (every year 1 h, PG)

For students of the doctoral school Computer Science (Informatik) – the seminar is compulsory, the aim is to help the doctoral candidates to improve their research work and their communicationa and presentation of their scientific field. Go to Course Homepage


706.315 Selected Topics on Interactive Knowledge Discovery 2014
706.315 Selected Topics on Interactive Knowledge Discovery 2014

Our data-centric world – from genome sequencing to digital surveys of space – generates tremendous amounts of complex high-dimensional data sets. Approaches from algebraic topology may help to understand such data, however, the challenge is in making such approaches interactive, hence to include the human into the loop at the very beginning of the knowledge discovery and data mining process. https://online.tugraz.at/tug_online/lv.detail?cperson_nr=5313&clvnr=175496


444.152 Medical Informatics / Medizinische Informatik
444.152 Medical Informatics / Medizinische Informatik

2VO, 3 ECTS, WS 13/14, Course starts: Di, 15.10.2013, Graz University of Technology, Faculty of Electrical and Information Engineering, Insitute of Genomics and Bioinformatics; The focus of this lecture is on knowledge discovery and data mining [Link to TUG-Online], all lecture slides available via: http://genome.tugraz.at/medical_informatics.shtml


706.046 AK HCI Mensch-Maschine Kommunikation: Applying User-Centered Design 2014
706.046 AK HCI Mensch-Maschine Kommunikation: Applying User-Centered Design 2014

3 VU, 5 ECTS, SS 13, Selected chapters of Human–Computer Interaction & Usability Engineering (HCI&UE), Graz University of Technology, Faculty of Informatics, Institute for Information Systems and Computer Media (IICM), [Link to TUG-Online]


706.117 DiplomandInnen Seminar (every year, 5 ECTS, 3 h, G)
706.117 DiplomandInnen Seminar (every year, 5 ECTS, 3 h, G)

3 SE, 5 ECTS, WS 12/13, Diplomandinnen und Diplomanden Seminar, Graz University of Technology, Faculty of Informatics, Institute for Information Systems and Computer Media (IICM), [Link to TUGOnline]


Probabilistic Decision Making and Statistical Learning Mini-Course (since 2010) blocked Mini-Course), (3 ECTS, 1h, PG)

This Mini-Course is an introduction into a core area of health informatics and helps to understand decision making generally and how human intelligence can be augmented by Artificial Intelligence (AI) and Machine Learning (ML) specifically. 

Course Homepage: https://human-centered.ai/mini-course-make-decisions-practice-2019

 


400.141 Knowledge, Information and Visualiszation 2006-2011 (compulsory, each semester, 3 ECTS, 3 h, UG, G)
400.141 Knowledge, Information and Visualiszation 2006-2011 (compulsory, each semester, 3 ECTS, 3 h, UG, G)

This course is compulsory for graduate medical students, and postgraduate PhD students of life sciences. The course covers principles of information systems, fundamentals of decision making and focuses on decision support systems (with hands-on exercises).