|
|
course list >> Technische Fakultät (Tech) >> Artificial Intelligence (AI) >>
|
Lehrveranstaltungsverzeichnis Masterstudiengang Artificial Intelligence (AI)
| |
Master-Projekt Datenmanagement [MastProj] -
- Lecturers:
- Richard Lenz, Alle Assistenten
- Details:
- Projektseminar, 2 cred.h, ECTS: 10, nur Fachstudium
- Dates:
- unregelmäßig, nach Bedarf
- Fields of study:
- WPF AI-MA 3
- Contents:
- Da wir in der Vergangenheit immer mit sehr kleinen Teilnehmerzahlen in unseren Master-Projekten zu tun hatten, haben wir sie nun (nach dem Vorbild anderer Lehrstühle) anders organisiert:
Die Teilnehmer erhalten individuelle Aufgaben, die sich in den Projekten am Lehrstuhl ergeben haben und die sich im Rahmen einer solchen Lehrveranstaltung lösen lassen. Sowohl die Wissenschaftlichkeit als auch die erwünschte Team-Arbeit sind durch die Einbettung in diese Projekte gegeben, selbst bei nur einem Teilnehmer oder einer Teilnehmerin. Im Unterschied zu den Examensarbeiten wird die praktische Arbeit einen viel größeren Anteil einnehmen. Literaturarbeit und Dokumentation der Ergebnisse sind immer noch erwünscht, fallen aber deutlich geringer aus als bei Examensarbeiten. In erster Linie wird an Forschungsprototypen mitgearbeitet, die in den Projekten am Lehrstuhl erstellt werden. Das kann Codierung bedeuten, aber auch Messungen und Simulationen, um nur einige Beispiele zu nennen. Wir schlagen Themen vor, aber es ist durchaus zulässig, sich auch selbst Gedanken über ein Thema zu machen. Naheliegende Voraussetzung dafür ist es, sich mit den Projekten am Lehrstuhl zu befassen (siehe Orientierungsvorlesung!) und auch mit den Mitarbeitern zu sprechen, die diese Projekte durchführen. Themenvorschläge finden sich im zugeordneten StudOn-Kurs:
https://www.studon.fau.de/crs1948594.html
- Keywords:
- Master; Projekt; Project; Masterprojekt; Master Projekt; EDEN; BATS; TDQMed; DSAM
|
| |
Fantastic datasets and where to find them [FANDAT] -
- Lecturer:
- Andreas Kist
- Details:
- Seminar, 2 cred.h, graded certificate, ECTS: 2,5, nur Fachstudium
- Dates:
- Thu, 13:15 - 14:45, Zoom-Meeting
starting 22.4.2021
- Fields of study:
- WPF AI-MA ab 1
- Contents:
- Im ersten Zoom-Meeting werden verschiedene biomedizinische Datensätze aufgezeigt, wo man diese finden kann und als Vortrag vergeben. Ziel des Seminars ist es, dass Studenten durch das Vorstellen eines biomedizinischen Datensatzes die Grundlagen der Datenakquise, den Umfang des Datensatzes, sowie die Vor- und Nachteile eines Datensatzes verstehen.
|
| |
Maschinelles Lernen und Datenanalytik für Industrie 4.0 [MADI40] -
- Lecturers:
- Björn Eskofier, An Nguyen, Franz Köferl, Philipp Schlieper, Christoph Scholl
- Details:
- Seminar, 2 cred.h, graded certificate, ECTS: 5, nur Fachstudium, Registration via mail to an.nguyen@fau.de
- Dates:
- Wed, 16:15 - 18:00, 00.010
Starts on 14.04.2021
- Fields of study:
- WPF AI-MA ab 1
- Prerequisites / Organisational information:
- Prerequisites
Registration via e-mail to an.nguyen@fau.de Registration period: 15.02-19.04.2021
This course will be held online until the coronavirus pandemic is contained to such an extent that the Bavarian state government can allow face-to-face teaching again. More information will be sent via mail to registered students. Requirements:
Prior knowledge of machine learning via courses like PA, IntroPR, PR, DL, MLTS, CVP or equivalent (ideally first project experiences) is expected! Motivation to explore scientific findings (e.g. via literature research) Motivation to code and analyze data
Examination:
50% of grade: Presentation + demo (20 minutes)
50% of grade 4 pages IEEE standard paper (excluding references) + code submission
Attending the presentations of other students
- Contents:
- Contents
Companies in all kinds of industries are producing and collecting rapidly more and more data from various sources. This is enabled by technologies such as the Internet of Things (IoT), Cyber-physical system (CPS) and cloud computing. Hence there is an increasing demand in industry and research for students and graduates with machine learning and data analytics skills in the Industry 4.0 context.
In this Seminar the Industry 4.0 term will include the medical device sector. Aim of this seminar is to give students insights about state-of-the-art machine learning and data analytics methods and applications in the Industry 4.0 and Healthcare context. Students will mainly work independently on specific topics including implementation and analytical components. Several potential topics will be provided but students are also encouraged to propose their own topics (please discuss with teaching staff beforehand). Topics covered will include but are not limited to:
Best practices for presentation and scientific work
Overview of current hot topics in the field of machine learning and data analytics for Industry 4.0 (e.g. deep learning for predictive maintenance and process mining for usage analysis)
Data acquisition (what kind of data can be acquired? Identification of publicly available data sets) and storage (how can data be stored efficiently?)
Machine learning and data analytics methodologies (Support vector machines, Hidden Markov models, Deep learning, Process mining, etc.) for industrial data (sensor data, event logs, ...)
Object detection in industry application
The seminar will include talks by corresponding lecturer and invited experts in the domain. Furthermore, students will present results from literature research and data analytics projects (provided or open source datasets). Learning Objectives and Competencies
Students will develop an understanding of the current hot field of machine learning and data analytics for Industry 4.0 / healthcare
Students will learn to research and present a topic within the context of machine learning and data analytics for Industry 4.0 / healthcare independently
Students will learn to identify opportunities, challenges and limitations of corresponding ML approaches for Industry 4.0 / healthcare
Students will develop the skill to identify and understand relevant literature and to present their finding in a structured manner
Students will learn to present implementation and validation results in form of a demonstration and/or report
- Recommended literature:
- Literature (Selection)
Lei, Yaguo, Naipeng Li, Liang Guo, Ningbo Li, Tao Yan, and Jing Lin. “Machinery Health Prognostics: A Systematic Review from Data Acquisition to RUL Prediction.” Mechanical Systems and Signal Processing 104 (May 2018): 799–834.https://doi.org/10.1016/j.ymssp.2017.11.016. Rojas, Eric, Jorge Munoz-Gama, Marcos Sepúlveda, and Daniel Capurro. “Process Mining in Healthcare: A Literature Review.” Journal of Biomedical Informatics 61 (June 1, 2016): 224–36. https://doi.org/10.1016/j.jbi.2016.04.007. Wil M. P. van der Aalst. „Process Mining: Data Science in Action” 2nd edition, Springer 2016. ISBN 978-3-662-49851-4 Wang, Lihui, and Xi Vincent Wang. Cloud-Based Cyber-Physical Systems in Manufacturing. Cham: Springer International Publishing, 2018. https://doi.org/10.1007/978-3-319-67693-7.
- Keywords:
- Machine Learning, Data Analytics, Process Mining, Predictive Maintenance, Industry 4.0, Healthcare
|
| |
Seminar AI for Healthcare: Challenges in Translating Promises into Patient Outcomes [AIOutcomes] -
- Lecturers:
- Katharina Breininger, Mathias Unberath, Nishant Ravikumar
- Details:
- Seminar, 2 cred.h, ECTS: 5, This course will be conducted online. Registration will be enabled via StudOn starting in May. If you are interested in attending the seminar, please send an email to katharina.breininger@fau.de.
- Fields of study:
- WPF AI-MA ab 1
- Prerequisites / Organisational information:
- FAU students register for the course in StudOn. Registration will be enabled via StudOn starting in May. If you are interested in attending the seminar, please send an email to katharina.breininger@fau.de.
The seminar is offered as a compact course during summer intersession in September (exact dates are tbd).
This course is offered under the prerequisite that the corresponding funding for Prof. Dr.-Ing. Mathias Unberath and Dr. Nishant Ravikumar is granted by FAU.
- Contents:
- Artificial Intelligence in general, and machine learning (AI/ML) in particular, have become a major thrust of healthcare research. Concisely, it is now widely accepted that learning-based approaches will be a core building block of personalized and precision medicine. The reasons for this are twofold: First, these methods either automate data analysis tasks that would be intractable otherwise thus paving the way for innovative decision making; and second, they offer recommendations in high-variance decisions based on population-scale evidence used for their development, thus potentially decoupling provider experience and outcomes.
Unfortunately, most of the recent successes on private in house or public grand challenge data have been linked to neither improved outcomes nor clinical impact but are limited to task-based comparisons in sandbox settings. Furthermore, developed techniques that have been validated thoroughly in a research setting often fail/perform poorly in clinical ones, and do not account for inherent biases in the data and/or experimental setup.
In this seminar, we will review recently published research on AI/ML for healthcare that successfully translated into clinical practice to identify key factors in study design, method development, infrastructure, or regulation that enable translation.
The seminar will focus on three distinct areas: digital pathology, medical image computing, and computer-aided interventions. Where possible, guest lectures from academia, clinics, as well as industry will be invited as part of the seminar.Students will be able to
Students will have acquired competences to
perform an unstructured literature review on an assigned subject
independently research the assigned subject
present and introduce the subject to their peers
give a scientific presentation in English according to international conference standards
summarize their findings in a written report that adheres to good scientific practice
The overall grade consists of two parts: A 30-minute seminar presentation (50% final grade, comprised of content and delivery). The goal of the seminar is to prepare a topic for other students in an accessible way. After all groups have presented their topics, we will break out into smaller teams to further process the seminar talk contents and synergize them into a paper-style report and report-out (conference-style) presentation (~4 pages IEEE and 10 minutes, respectively; 50% final grade, comprised of content and delivery) that discusses at least one core challenge identified throughout the seminar and proposes community guidelines to improve translation of AI research into clinical practice. Talks and seminar paper should be in English.
Students will work in groups of two if the number of participants allows.
- Recommended literature:
- Unberath, M., Ghobadi, K., Levin, S., Hinson, J., & Hager, G. D. (2020). Artificial Intelligence‐Based Clinical Decision Support for COVID-19–Where Art Thou?. Advanced Intelligent Systems, 2(9), 2000104.
Christopher J. Kelly, Alan Karthikesalingam, Mustafa Suleyman, Greg Corrado & Dominic King: Key challenges for delivering clinical impact with artificial intelligence, BMC Medicine, Vol. 17, Article number: 195 (2019)
Adam Bohr and Kaveh Memarzadeh (eds.): Artificial Intelligence in Healthcare, Academic Press (2020)
Herein for example:
Sara Gerke, Timo Minssen, Glenn Cohen: Chapter 12 - Ethical and legal challenges of artificial intelligence-driven healthcare, Adam Bohr, Kaveh Memarzadeh, (eds.), Artificial Intelligence in Healthcare, Academic Press, pp. 295-336 (2020)
| | | | tbd. | | | |
N.N. | |
| |
Seminar Artificial Intelligence and Neuroscience [SemAINeuro] -
- Lecturers:
- Andreas Maier, Patrick Krauß, Joachim Hornegger
- Details:
- Seminar, 2 cred.h, ECTS: 5, nur Fachstudium, This course will be held online until the coronavirus pandemic is contained to such an extent that the Bavarian state government can allow face-to-face teaching again. Information regarding the online teaching will be provided in the studon course.
- Dates:
- Mon, 8:15 - 9:45, KH 1.021
- Fields of study:
- WPF AI-MA ab 1
- Prerequisites / Organisational information:
- Registrierung via StudOn:
https://www.studon.fau.de/crs3687384.html
- Contents:
- Neuroscience has played a key role in the history of artificial intelligence (AI), and has been an inspiration for building human-like AI, i.e. to design AI systems that emulate human intelligence. Furthermore, transferring design and processing principles from biology to computer science promises novel solutions for contemporary challenges in the field of machine learning. This research direction is called neuroscience-inspired artificial intelligence.
In addition, neuroscience provides a vast number of methods to decipher the representational and computational principles of biological neural networks, which can in turn be used to understand artificial neural networks and help to solve the so called black box problem. This endeavour is called neuroscience 2.0 or machine behaviour.
Finally, the idea of combining artificial intelligence, in particular deep learning, and computational modelling with neuroscience and cognitive science has recently gained popularity, leading to a new research paradigm for which the term cognitive computational neuroscience has been coined. There is increasing evidence that, even though artificial neural networks lack biological plausibility, they are nevertheless well suited for modelling brain function.
The seminar will cover the most important works which provide the cornerstone knowledge to understand cutting edge research at the intersection of AI and neuroscience.Students will be able to • independently identify challenges in translating technical solutions from the bench to the bedside, and assess how close to clinical feasibility a technical solution is Students will have acquired competences to • perform an unstructured literature review on an assigned subject
• independently research the assigned subject
• present and introduce the subject to their peers
• give a scientific presentation in English according to international conference standards
• summarize their findings in a written report that adheres to good scientific practice
- Recommended literature:
- Barak, O. (2017). Recurrent neural networks as versatile tools of neuroscience research. Current opinion in neurobiology, 46, 1-6.
Barrett, D. G., Morcos, A. S., & Macke, J. H. (2019). Analyzing biological and artificial neural networks: challenges with opportunities for synergy?. Current opinion in neurobiology, 55, 55-64.
Cichy, R. M., Khosla, A., Pantazis, D., Torralba, A., & Oliva, A. (2016). Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence. Scientific reports, 6(1), 1-13.
Cichy, R. M., & Kaiser, D. (2019). Deep neural networks as scientific models. Trends in cognitive sciences, 23(4), 305-317.
Dasgupta, S., Stevens, C. F., & Navlakha, S. (2017). A neural algorithm for a fundamental computing problem. Science, 358(6364), 793-796.
Hassabis, D., Kumaran, D., Summerfield, C., & Botvinick, M. (2017). Neuroscience-inspired artificial intelligence. Neuron, 95(2), 245-258.
Kriegeskorte, N., & Douglas, P. K. (2018). Cognitive computational neuroscience. Nature neuroscience, 21(9), 1148-1160.
Marblestone, A. H., Wayne, G., & Kording, K. P. (2016). Toward an integration of deep learning and neuroscience. Frontiers in computational neuroscience, 10, 94.
Nasr, K., Viswanathan, P., & Nieder, A. (2019). Number detectors spontaneously emerge in a deep neural network designed for visual object recognition. Science advances, 5(5), eaav7903.
Rahwan, I., Cebrian, M., Obradovich, N., Bongard, J., Bonnefon, J. F., Breazeal, C., ... & Wellman, M. (2019). Machine behaviour. Nature, 568(7753), 477-486.
Yamins, D. L., & DiCarlo, J. J. (2016). Using goal-driven deep learning models to understand sensory cortex. Nature neuroscience, 19(3), 356-365.
Jonas, E., & Kording, K. P. (2017). Could a neuroscientist understand a microprocessor?. PLoS computational biology, 13(1), e1005268.
- Keywords:
- algorithms; medical image processing
|
| |
Project Machine Learning and Data Analytics [ProjMAD] -
- Lecturers:
- Björn Eskofier, Dario Zanca, An Nguyen
- Details:
- Sonstige Lehrveranstaltung, graded certificate, ECTS: 10, Registration via email to dario.zanca@fau.de or an.nguyen@fau.de
- Dates:
- Thu, 16:15 - 18:00, 00.010
- Fields of study:
- WPF AI-MA ab 1
- Prerequisites / Organisational information:
- Master Studium Informatik
Kick-off seminar on first Thursday of each semester (SS2021 - 15.04.2021)
Depending on the topic knowledge from courses like PR, PA, DL, MLTS or CV including good Python programming skills are required.
Motivation to code and experiment
- Contents:
- There will be a kick-off meeting the first Thursday 16:15-18:00 of each semester where topics in the field of machine learning and data analytics will be presented. Most topics will be related to the diverse research fields of the Machine Learning and Data Analytics Lab. Students also have the possibility to discuss their own project ideas with the supervisors. The distribution of topics will be based on prerequisites and first come, first serve in terms of time of registration until all topics are distributed.
- Keywords:
- Master Projekt Project
|
| |
The AMOS Project (Exercise) [OSS-AMOS-UE] -
- Lecturer:
- Dirk Riehle
- Details:
- Übung, ECTS: 5
- Fields of study:
- WPF AI-MA ab 1
- Prerequisites / Organisational information:
- ALL COURSES WILL BE MANAGED FULLY ONLINE UNTIL WE CAN RETURN TO IN-PERSON TEACHING.
- Contents:
- This course teaches agile methods (Scrum and XP) and open source tools using a single semester-long project.
Topics covered are:
Agile methods and related software development processes Scrum roles, process practices, including product and engineering management Technical practices like refactoring, continuous integration, and test-driven development Principles and best practices of open source software development
The project is a software development project in which student teams work with an industry partner who provides the idea for the project. This is a practical hands-on experience. Students can play one of two primary roles:
Product owner. In this function, a student defines, prioritizes, communicates, and reviews requirements. The total effort adds up to 5 ECTS. Software developer. In this function, a student estimates their effort for requirements and implements them. The total effort adds up to 10 ECTS.
Students will be organized into teams of 5-7 people, combining product owners with software developers. An industry partner will provide requirements to be worked out in detail by the product owners and to be realized by the software developers. The available projects will be presented in the run-up to the course. Class consists of a 90min lecture followed by a 90min team meeting. Rooms and times for team meetings are assigned in the beginning of the semester. Schedule and sign-up are available at https://oss.cs.fau.de/oss-amos-course. Please sign up for the course on StudOn (available through previous link) as soon as possible.
| | | | | 14:15 - 15:45 | n.V. | |
Riehle, D. | |
| | | | 14:15 - 15:45 | n.V. | |
Riehle, D. | |
| | | Wed | 12:30 - 14:00 | n.V. | |
Riehle, D. | |
| | | Wed | 12:30 - 14:00 | n.V. | |
Riehle, D. | |
| | | Wed | 12:30 - 14:00 | n.V. | |
Riehle, D. | |
| | | Wed | 12:30 - 14:00 | n.V. | |
Riehle, D. | |
| | | Wed | 12:30 - 14:00 | n.V. | |
Riehle, D. | |
| | | Wed | 12:30 - 14:00 | n.V. | |
Riehle, D. | |
| | | Wed | 18:15 - 19:45 | n.V. | |
Riehle, D. | |
| |
Artificial Intelligence II [AI II] -
- Lecturer:
- Michael Kohlhase
- Details:
- Vorlesung, 4 cred.h, Artificial Intelligence II will take place this semester, probably online. For details, see the announcements at https://fsi.cs.fau.de/forum/149-Kuenstliche-Intelligenz-II
- Dates:
- Wed, 10:15 - 11:45, H8
Tue, 8:15 - 9:45, HH
Artificial Intelligence II will be online this semester. For details, see the announcements on StudOn
- Fields of study:
- WPF AI-MA ab 1
WPF AI-MA ab 1
- Contents:
- Artificial Intelligence II will be online this semester. Details will be announced on StudOn
Dieser Kurs beschäftigt sich mit den Grundlagen der Künstlichen Intelligenz (KI), insbesondere mit Techniken des Schliessens unter Unsicherheit, des maschinellen Lernens und dem Sprachverstehen.
Der Kurs baut auf der Vorlesung Künstliche Intelligenz I vom Wintersemester auf und führt diese weiter. Lernziele und Kompetenzen
Fach- Lern- bzw. Methodenkompetenz
Wissen: Die Studierenden lernen grundlegende Repräsentationsformalismen und Algorithmen der Künstlichen Intelligenz kennen.
Anwenden: Die Konzepte werden an Beispielen aus der realen Welt angewandt (Übungsaufgaben).
Analyse: Die Studierenden lernen über die Modellierung in der Maschine menschliche Intelligenzleistungen besser einzuschätzen.
Sozialkompetenz
- Recommended literature:
- Die Vorlesung folgt weitgehend dem Buch
Stuart Russell und Peter Norvig: Artificial Intelligence: A Modern Approach. Prentice Hall, 3rd edition, 2009.
Deutsche Ausgabe:
Stuart Russell und Peter Norvig: Künstliche Intelligenz: Ein Moderner Ansatz. Pearson-Studium, 2004 (Übersetzung der 2.Auflage).
ISBN: 978-3-8273-7089-1
|
| |
Cognitive Neuroscience for AI Developers [CNAID] -
- Lecturers:
- Patrick Krauß, Andreas Kist, Andreas Maier
- Details:
- Vorlesung, 4 cred.h, ECTS: 5, nur Fachstudium, This course will be held online until the coronavirus pandemic is contained to such an extent that the Bavarian state government can allow face-to-face teaching again. Information regarding the online teaching will be provided in the studon course.
- Dates:
- Tue, 14:15 - 15:45, 09.150
Thu, 10:15 - 11:45, 09.150
- Fields of study:
- WPF AI-MA ab 1
- Prerequisites / Organisational information:
- FAU students register for the written exam via meinCampus.
https://www.studon.fau.de/crs3690005.html
- Contents:
- Neuroscience has played a key role in the history of artificial intelligence (AI), and has been an inspiration for building human-like AI, i.e. to design AI systems that emulate human intelligence.
Neuroscience provides a vast number of methods to decipher the representational and computational principles of biological neural networks, which can in turn be used to understand artificial neural networks and help to solve the so called black box problem. This endeavour is called neuroscience 2.0 or machine behaviour. In addition, transferring design and processing principles from biology to computer science promises novel solutions for contemporary challenges in the field of machine learning. This research direction is called neuroscience-inspired artificial intelligence.
The course will cover the most important works which provide the cornerstone knowledge to understand the biological foundations of cognition and AI, and applications in the areas of AI-based modelling of brain function, neuroscience-inspired AI and reverse-engineering of artificial neural networks.
- Recommended literature:
- Gazzaniga, Michael. Cognitive Neuroscience - The Biology of the Mind. W. W. Norton & Company, 2018.
Ward, Jamie. The Student's Guide to Cognitive Neuroscience. Taylor & Francis Ltd., 2019.
Bermúdez, José Luis. Cognitive Science: An Introduction to the Science of the Mind. Cambridge University Press, 2014.
Friedenberg, Jay D., and Silverman, Gordon W. Cognitive Science: An Introduction to the Study of Mind. SAGE Publications, Inc., 2015.
Gerstner, Wulfram, et al. Neuronal dynamics: From single neurons to networks and models of cognition. Cambridge University Press, 2014.
|
| |
Computer Vision [CV] -
- Lecturers:
- Vincent Christlein, Ronak Kosti
- Details:
- Vorlesung, 2 cred.h, ECTS: 2,5, nur Fachstudium
- Dates:
- Mon, 8:15 - 9:45, H4
- Fields of study:
- WPF AI-MA ab 1
- Contents:
- This lecture discusses important algorithms from the field of computer vision. The emphasis lies on 3-D vision algorithms, covering the geometric foundations of computer vision, and central algorithms such as stereo vision, structure from motion, optical flow, and 3-D multiview reconstruction. The course will also introduce Convolutional Neural Networks (with some examples to play around) and discuss it's importance and impact. Participants of this advanced course are expected to bring experience from prior lectures either from the field of pattern recognition or from the field of computer graphics.
Due to the unfortunate situation with the coronavirus (as of April 2020), it is not possible to start the course in the traditional face-to-face manner. We start with an 'inverted classroom' approach, where we pre-record lectures and upload them. Students are required to watch them before the actual lecture period. The actual lecture period (over Zoom) is dedicated to solving doubts and answering queries that students might have for the lectures watched.
- Recommended literature:
- Richard Szeliski: Computer Vision: Algorithms and Applications, Springer 2011.
Richard Hartley and Andrew Zisserman: Multiple view geometry in Computer Vision. Cambridge university press, 2003.
- Keywords:
- computer vision; stereo vision; structure from motion; multi-view reconstruction; convolutional neural networks
|
| |
Deep Learning [DL] -
- Lecturer:
- Andreas Maier
- Details:
- Vorlesung, 2 cred.h, ECTS: 2,5, nur Fachstudium, Information regarding the online teaching will be added to the studon course
- Dates:
- Tue, 16:15 - 17:45, H4
- Fields of study:
- WPF AI-MA ab 1
- Prerequisites / Organisational information:
- The following lectures are recommended:
https://www.studon.fau.de/crs3729302.html
- Contents:
- Deep Learning (DL) has attracted much interest in a wide range of applications such as image recognition, speech recognition and artificial intelligence, both from academia and industry.
This lecture introduces the core elements of neural networks and deep learning, it comprises:
(multilayer) perceptron, backpropagation, fully connected neural networks loss functions and optimization strategies convolutional neural networks (CNNs) activation functions regularization strategies common practices for training and evaluating neural networks visualization of networks and results common architectures, such as LeNet, Alexnet, VGG, GoogleNet recurrent neural networks (RNN, TBPTT, LSTM, GRU) deep reinforcement learning unsupervised learning (autoencoder, RBM, DBM, VAE) generative adversarial networks (GANs) weakly supervised learning applications of deep learning (segmentation, object detection, speech recognition, ...)
The accompanying exercises will provide a deeper understanding of the workings and architecture of neural networks.
- Recommended literature:
- Ian Goodfellow, Yoshua Bengio, Aaron Courville: Deep Learning. MIT Press, 2016
Christopher Bishop: Pattern Recognition and Machine Learning, Springer Verlag, Heidelberg, 2006 Yann LeCun, Yoshua Bengio, Geoffrey Hinton: Deep learning. Nature 521, 436–444 (28 May 2015)
- Keywords:
- deep learning; machine learning
|
| |
Deep Learning Exercises [DL E] -
- Lecturers:
- Florian Thamm, Zijin Yang, Noah Maul, Karthik Shetty
- Details:
- Übung, 2 cred.h, ECTS: 2,5, nur Fachstudium, This course will be held online until the coronavirus pandemic is contained to such an extent that the Bavarian state government can allow face-to-face teaching again. Information regarding the online teaching will be added to the studon course
- Fields of study:
- WPF AI-MA ab 1
- Keywords:
- deep learning; machine learning
| | | | Mon | 12:00 - 14:00 | 0.01-142 CIP | |
Thamm, F. | |
| | | Tue | 18:00 - 20:00 | 0.01-142 CIP | |
Thamm, F. | |
| | | Wed | 16:00 - 18:00 | 0.01-142 CIP | |
Thamm, F. | |
| | | Thu | 14:00 - 16:00 | 0.01-142 CIP | |
Thamm, F. | |
| | | Fri | 8:00 - 10:00 | 0.01-142 CIP | |
Thamm, F. | |
| |
Human Computer Interaction [HCI] -
- Lecturer:
- Björn Eskofier
- Details:
- Vorlesung, 3 cred.h, ECTS: 3,75
- Dates:
- Mon, 8:15 - 9:45, H10
Fri, 10:15 - 11:45, H10
- Fields of study:
- WPF AI-MA ab 1
- Prerequisites / Organisational information:
- Folien zur Vorlesung und Organisation über Studon.
- Contents:
- Studon Kurs:
https://www.studon.fau.de/crs3663032.html
Aufgrund der derzeitigen Corona-Lage findet die Vorlesung digital statt. Für weitere Informationen, wie man sich in die digitalen Räume einloggen kann, besuchen Sie bitte unseren zugehörigen StudOn Kurs.
- Keywords:
- human-computer interaction, Mensch-Maschine-Schnittstelle, grafische Benutzerschnittstellen, mobile Mensch-Computer-Interaktion, Mensch-Maschine-Interaktion im Fahrzeug, ubiquitäre und eingebettete interaktive Systeme
|
| |
Human Computer Interaction Exercises [HCI-E] -
- Lecturer:
- Wolfgang Mehringer
- Details:
- Übung, 1 cred.h, ECTS: 1,25
- Dates:
- Mon, 14:15 - 15:45, K1-119 Brose-Saal
- Fields of study:
- WPF AI-MA ab 1
- Contents:
- Aufgrund der derzeitigen Corona-Lage findet die Übung digital statt. Für weitere Informationen, wie man sich in die digitalen Räume einloggen kann, besuchen Sie bitte unseren zugehörigen StudOn Kurs.
- Keywords:
- human-computer interaction, Mensch-Maschine-Schnittstelle, grafische Benutzerschnittstellen, mobile Mensch-Computer-Interaktion, Mensch-Maschine-Interaktion im Fahrzeug, ubiquitäre und eingebettete interaktive Systeme
|
| |
Medical Image Processing for Diagnostic Applications (VHB course) [MIPDA] -
- Lecturers:
- Andreas Maier, Tristan Gottschalk, Celia Martín Vicario, Julian Hoßbach
- Details:
- Vorlesung, 4 cred.h, ECTS: 5
- Dates:
- to be determined
- Fields of study:
- WPF AI-MA ab 1
- Prerequisites / Organisational information:
- Requirements: mathematics for engineering
Organization:
This is an online course of Virtuelle Hochschule Bayern (VHB).
Go to https://www.vhb.org to register to this course.
FAU students register for the written exam via meinCampus.
- Contents:
- Medical imaging helps physicians to take a view inside the human body and therefore allows better treatment and earlier diagnosis of serious diseases.
However, as straightforward as the idea itself is, so diversified are the technical difficulties to overcome when implementing a clinically useful imaging device. We begin this course by discussing all available modalities and the actual imaging goals which highly affect the imaging result. Some modalities produce very noisy results, but there are multiple other artifacts that show up in raw acquisition data and have to be dealt with. We address these issues in the chapter preprocessing and show how to compensate for image distortions, how to interpolate defect pixels, and finally correct bias fields in magnetic resonance images. The largest portion of this course covers the theory of medical image reconstruction. Here, from a set of projections from different viewing angles a 3-D image is merged that allows a definite localization of anatomical and pathological features. Following roughly the historical development of CT devices, we study the process from parallel beam to fan beam geometry and include a discussion of phantoms as a tool for calibration and image quality assessment. We then move forward and learn about reconstruction in 3-D. Since the system matrix often grows in dimensions such that many direct solvers become infeasible, we also discuss pros and cons of iterative methods. In the final chapter, image registration is introduced as the concept of computing the mapping that maps the content of one image to another. Two different acquisitions usually result in images that are at least rotated and translated against each other. Image registration forms the set of tools that we need to match certain image features in order to align both images for further processing, image improvement or image overlays.
- Keywords:
- Mustererkennung, Medizinische Bildverarbeitung
|
| |
Computational Neurotechnology [Neurotech] -
- Lecturer:
- Tobias Reichenbach
- Details:
- Übung, 2 cred.h, ECTS: 2,5, nur Fachstudium
- Dates:
- Fri, 14:15 - 15:45, Zoom-Meeting
- Fields of study:
- WPF AI-MA 2
- Keywords:
- Neurotechnologie, neuroengineering, neurotechnology, computational, neuroscience, brain-machine-interface, brain-computer interface, neurorehabilitation
|
| |
Parallel Systems [PSys] -
- Lecturers:
- Frank Hannig, Jürgen Teich
- Details:
- Vorlesung, 2 cred.h, ECTS: 2,5, nur Fachstudium
- Dates:
- Thu, 10:15 - 11:45, 01.255-128
per Zoom, weitere Details nach Anmeldung via StudOn: https://www.studon.fau.de/crs3634603_join.html
- Fields of study:
- WPF AI-MA ab 1
- Contents:
- Selbst unser PC erlaubt bereits ein hohes Maß an nebenläufiger Verarbeitung von Daten. Die effiziente Ausnutzung von Parallelität bedarf allerdings auch spezieller Programmier- und Übersetzungstechniken. Beschrieben werden Eigenschaften unterschiedlicher paralleler Rechnerarchitekturen und Metriken zu deren Beurteilung. Weiterhin werden Modelle und Sprachen zum Programmieren paralleler Rechner eingeführt. Neben der Programmierung von allgemeinen Parallelrechnern werden Entwurfsmethoden (CAD) vorgestellt, wie man ausgehend von einer algorithmischen Problemstellung massiv parallele Rechenfelder in VLSI herleiten kann. Im Einzelnen werden behandelt:
1. Theorie der Parallelität (parallele Computermodelle, parallele Spezifikationsformen und -sprachen, Performanzmodelle und -berechnung)
2. Klassifikation paralleler und skalierbarer Rechnerarchitekturen (Multiprozessoren und Multicomputer, Vektorrechner, Datenflussmaschinen, VLSI-Rechenfelder)
3. Programmierung paralleler Rechner (Sprachen und Modelle, Entwurfsmethoden und Compiler, Optimierung)
4. Massive Parallelität: Vom Algorithmus zur Schaltung Theoretische und praktische Übungen mit rechnergestützten Werkzeugen
|
| |
Erweiterte Übungen zu Parallele Systeme [EU-PSys] -
- Lecturers:
- Michael Witterauf, Stefan Groth, Marcel Brand, Frank Hannig
- Details:
- Übung, 2 cred.h, ECTS: 2,5
- Dates:
- Thu, 14:00 - 18:00, 02.133-128
Wed, 8:00 - 12:00, 02.133-128
single appointment on 8.6.2021, single appointment on 6.7.2021, single appointment on 13.7.2021, 9:00 - 13:00, 02.133-128
single appointment on 14.7.2021, 10:00 - 14:00, 02.133-128
single appointment on 16.7.2021, 9:00 - 13:00, 14:00 - 18:00, 02.133-128
verpflichtend, vor Ort an den Rechnerarbeitsplätzen des Lehrstuhls
- Fields of study:
- WPF AI-MA ab 1
|
| |
Pattern Analysis [PA] -
- Lecturer:
- Christian Riess
- Details:
- Vorlesung, 3 cred.h, graded certificate, ECTS: 3,75, This course will be held online until the coronavirus pandemic is contained to such an extent that the Bavarian state government can allow face-to-face teaching again
- Dates:
- Tue, Fri, 12:15 - 13:45, H16
- Fields of study:
- WPF AI-MA ab 1
- Prerequisites / Organisational information:
- Please join the class "Pattern Analysis" in studOn. All lecture material will be linked and made available there.
It is recommended (but not mandatory) that participants attend the lecture Pattern Recognition first.
- Contents:
- This lecture complements the lectures "Introduction to Pattern Recognition" and "Pattern Recognition".
In this third edition, we focus on analyzing and simplifying feature representations.
Major topics of this lecture are density estimation, clustering, manifold learning, hidden Markov models, conditional random fields, and random forests.
The lecture is accompanied by exercises, where theoretical results are
practically implemented and applied.
To participate, please join the Pattern Analysis studOn class: https://www.studon.fau.de/crs3708405_join.html
- Recommended literature:
- Christopher Bishop: Pattern Recognition and Machine Learning, Springer Verlag, Heidelberg, 2006
T. Hastie, R. Tibshirani, J. Friedman: The Elements of Statistical Learning, 2nd edition, Springer Verlag, 2017.
Antonio Criminisi and J. Shotton: Decision Forests for Computer Vision and Medical Image Analysis, Springer, 2013
- Keywords:
- pattern recognition, pattern analysis
|
| |
Speech Understanding [SLU] -
- Lecturer:
- Andreas Maier
- Details:
- Vorlesung, 2 cred.h, graded certificate, ECTS: 5, nur Fachstudium
- Dates:
- Wed, 16:15 - 17:45, 01.151-128
- Fields of study:
- WPF AI-MA ab 1
- Prerequisites / Organisational information:
- https://www.studon.fau.de/crs3717775.html
Für diese Lehrveranstaltung ist eine Anmeldung erforderlich.
Die Anmeldung erfolgt über: StudOn
- Contents:
- Nach Behandlung der grundlegenden Mechanismen menschlicher Spracherzeugung und Sprachwahrnehmung
gibt die Vorlesung eine detaillierte Einführung in (vornehmlich) statistisch orientierte Methoden der
maschinellen Erkennung gesprochener Sprache.
Schwerpunktthemen sind Merkmalgewinnung, Vektorquantisierung,
akustische Sprachmodellierung mit Hilfe von Markovmodellen, linguistische Sprachmodellierung mit Hilfe
stochastischer Grammatiken, prosodische Information
sowie Suchalgorithmen zur Beschleunigung des Dekodiervorgangs.
- Recommended literature:
- Niemann H.: Klassifikation von Mustern; Springer, Berlin 1983
Niemann H.: Pattern Analysis and Understanding; Springer, Berlin 1990 Schukat-Talamazzini E.G.: Automatische Spracherkennung;
Vieweg, Wiesbaden 1995 Rabiner L.R., Schafer R.: Digital Processing of Speech Signals;
Prentice Hall, New Jersey 1978 Rabiner L.R., Juang B.H.: Fundamentals of Speech Recognition;
Prentice Hall, New Jersey 1993
- Keywords:
- Mustererkennung, Merkmale, HMM, Sprachmodelle, Prosodie, Suchalgorithmen
|
| |
Swarm Intelligence (SI), formerly Organic Computing (OC) [SI] -
- Lecturer:
- Rolf Wanka
- Details:
- Vorlesung, 2 cred.h, ECTS: 2,5, Also for CE; Formerly known as Organic Computing (OC)
- Dates:
- Thu, 12:15 - 13:45, K1-119 Brose-Saal
- Fields of study:
- WPF AI-MA ab 1
- Contents:
- Unter Swarm Intelligence (SI) versteht man den Entwurf und den Einsatz von selbst-organisierenden Systemen, die sich den jeweiligen Umgebungsbedürfnissen dynamisch anpassen. Diese Systeme zeichnen sich dadurch aus, dass sie die sog. Self-*-Eigenschaft besitzen, d.h. sie sind selbst-konfigurierend, selbst-optimierend, selbst-heilend, selbst-schützend, selbst-erklärend, ...
Als Vorbild für solche technischen Systeme werden Strukturen und Methoden biologischer und anderer natürlicher Systeme gewählt.
- Recommended literature:
- Ch. Müller-Schloer, Ch. von der Malsburg, R. P. Würt. Organic Computing. Informatik-Spektrum, Band 27, Nummer 4, S. 332-336. (LINK)
I. C. Trelea. The particle swarm optimization algorithm: convergence analysis and parameter selection. Information Processing Letters 85 (2003) 317-325. (LINK) J. M. Kleinberg. Authoritative sources in a hyperlinked environment. Journal of the ACM 46 (1999) 604-632. (LINK) M. Dorigo. V. Maniezzo. A Colorni. Ant system: an autocatalytic optimizing process. Technical Report 91-016, Politecnico di Milano, 1991. (LINK) A. Badr. A. Fahmy. A proof of convergence for Ant algorithms. Information Sciences 160 (2004) 267-279. M. Clerc. J. Kennedy. The particle swarm - Explosion, stability, and convergence in a multidimensional complex space. IEEE Transactions on Evolutionary Computation 8 (2002) 58-73.
|
| |
The AMOS Project (Lecture) [OSS-AMOS-VL] -
- Lecturer:
- Dirk Riehle
- Details:
- Vorlesung, 2 cred.h, ECTS: 5
- Dates:
- Wed, 10:15 - 11:45, room tbd
- Fields of study:
- WPF AI-MA ab 1
- Prerequisites / Organisational information:
- ALL COURSES WILL BE MANAGED FULLY ONLINE UNTIL WE CAN RETURN TO IN-PERSON TEACHING.
- Contents:
- This course teaches agile methods (Scrum and XP) and open source tools using a single semester-long project.
Topics covered are:
Agile methods and related software development processes Scrum roles, process practices, including product and engineering management Technical practices like refactoring, continuous integration, and test-driven development Principles and best practices of open source software development
The project is a software development project in which student teams work with an industry partner who provides the idea for the project. This is a practical hands-on experience. Students can play one of two primary roles:
Product owner. In this function, a student defines, prioritizes, communicates, and reviews requirements. The total effort adds up to 5 ECTS. Software developer. In this function, a student estimates their effort for requirements and implements them. The total effort adds up to 10 ECTS.
Students will be organized into teams of 5-7 people, combining product owners with software developers. An industry partner will provide requirements to be worked out in detail by the product owners and to be realized by the software developers. The available projects will be presented in the run-up to the course. Class consists of a 90min lecture followed by a 90min team meeting. Rooms and times for team meetings are assigned in the beginning of the semester. Schedule and sign-up are available at https://oss.cs.fau.de/oss-amos-course. Please sign up for the course on StudOn (available through previous link) as soon as possible.
|
| |
Erweiterte Übungen zu Verteilte Systeme [EÜ VS] -
- Lecturers:
- Michael Eischer, Laura Lawniczak, Tobias Distler
- Details:
- Übung, 4 cred.h, ECTS: 5
- Dates:
- Tue, 10:00 - 12:00, 02.151-113 b CIP
starting 20.4.2021
- Fields of study:
- WPF AI-MA ab 1
- Prerequisites / Organisational information:
- Für diese Lehrveranstaltung ist eine Anmeldung erforderlich.
Die Anmeldung erfolgt von Donnerstag, 1.4.2021, 10:00 Uhr bis Freitag, 30.4.2021, 23:59 Uhr über: Waffel .
|
| |
Visual Computing in Medicine 2 [VCMed2] -
- Lecturers:
- Thomas Wittenberg, Peter Hastreiter
- Details:
- Vorlesung, ECTS: 2,5
- Dates:
- Wed, 14:15 - 15:45, H10
- Fields of study:
- WPF AI-MA ab 1
- Prerequisites / Organisational information:
- Until further notice, this course will take place in electronic form. Detailed information is provided in the StudOn-course "Visual Computing in Medicine 2 (VCMed 2) - summer term 2020".
Bis auf Weiteres findet der Kurs in elektronischer Form statt. Weitere Informationen finden Sie im StudOn-Kurs "Visual Computing in Medicine 2 (VCMed 2) - summer term 2020".
- Contents:
- Building onto the lecture VCMed1, VCMed2 provides examples of concrete solutions for diagnosis and therapy planning based on complex clinical images. It provides information how basic methods are selected and combined into practical applicable concepts. Examples from clinical applications will be used to relate strategies and requirements in clinical practice as well as the development process. Additionally, methods of medical image analysis and visualization are discussed in detail.
Linking methods of medical image analysis and visualization for processing diagostic and interventional questions Providing algorithmic approaches with concrete solution strategies for the processing of clinical iamges from the perspective of medical needs Overview of various medical imaging domains Multimodal image registration with non-rigid transformations Current topics of image-based diagnosis and therapy planning
- Recommended literature:
- P.M. Schlag, S. Eulenstein, Th. Lange „Computerassistierte Chirurgie", Elsevier Verlag 2010
H. Handels, „Medizinische Bildverarbeitung, Bildanalyse, Mustererkennung und Visualisierung für die computergestützte ärztliche Diagnostik und Therapie", Vieweg und Teubner Verlag, 2009 B. Preim, D. Bartz, "Visualization in Medicine - Theory, Algorithms, and Applications”, Morgan Kaufmann Verlag, 2007 E. Neri, D. Caramella, C. Bartolozzi, „Image Processing in Radiology", Springer Verlag, 2008 Th. Lehmann, W. Oberschelp, E. Pelikan, R. Pepges, „Bildverarbeitung für die Medizin", Springer Verlag, 1997
|
| |
Software-Anwendungen mit KI [OSS-SAKI-VUE] -
- Lecturer:
- Dirk Riehle
- Details:
- Vorlesung mit Übung, 2 cred.h, ECTS: 5
- Dates:
- Wed, 16:15 - 17:45, room tbd
- Fields of study:
- WPF AI-MA ab 1
- Prerequisites / Organisational information:
- ALL COURSES WILL BE MANAGED FULLY ONLINE UNTIL WE CAN RETURN TO IN-PERSON TEACHING.
- Contents:
- Dieser Kurs lehrt fortgeschrittene Methoden des maschinellen Lernens resp. der künstlichen Intelligenz anhand von vier nicht-trivialen Anwendungsbeispielen mit realen Daten aus der Industrie.
Jedes der vier Beispiele stellt eine umfangreiche Hausaufgabe für Studierende dar, in der unterschiedliche Problemarten (Korrelation, Klassifikation, etc.) mit unterschiedlichen Methoden (Clustering, Bayesian Networks, etc.) in unterschiedlichen Fachgebieten (Automobilindustrie, Finanzindustrie, etc.) kombiniert werden. Jede Aufgabe wird von einem dazugehörigen Industriepartner mitbetreut.
Die vier Beispiele werden nacheinander abgearbeitet und strukturieren die Kurszeit in vier gleich große Abschnitte von jeweils drei Wochen, von denen jeder Abschnitt dieselbe Struktur hat:
Vorbereitung auf den anstehenden Abschnitt durch Wiederholung relevanter Literatur Einführung in das Problem; Diskussion von Bibliotheken und Vorgehen zur Problemlösung Wiederholte Diskussion (zwei weitere Sitzungen) des Problems und der Herangehensweise Abgabe der Problemlösung, bestehend aus Erläuterung sowie Quelltext und Ergebnissen
Die Programmierung findet in Python statt; Studierende sollten entsprechende Fähigkeiten mitbringen oder sich zügig aneignen können. Es wird erwartet, dass Studierende aktiv mitarbeiten, sich etwaige fehlende Grundlagen selbst aneignen, und die technischen Aufgaben eigenständig lösen werden. Zeitplan und Registrierung sind unter https://oss.cs.fau.de/oss-saki-course zu finden. Bitte registrieren Sie sich auf StudOn (über vorigen Link findbar) sobald wie möglich.
|
| |
Virtual and Augmented Reality [VRAR] -
- Lecturers:
- Daniel Roth, Tutoren, Gastredner
- Details:
- Sonstige Lehrveranstaltung, 8 cred.h, graded certificate, ECTS: 10, nur Fachstudium, Combination of lecture (2 SWS) and practical course (6 SWS). Rückfragen, Verständnisfragen, sowie Prüfung können auch auf Deutsch abgelegt werden. --- Questions, comprehension questions, as well as examination can also be taken in German.
- Dates:
- Wed, 13:30 - 15:00, Zoom-Meeting
Neben den regelmäßigen Zoom Meetings wird (je nach Corona Maßnahmen) „Open Lab“ Möglichkeiten unter Einhaltung Corona Maßnahmen geben. --- In addition to regular Zoom meetings, there will be (depending on Corona measures) "Open Lab" opportunities while adhering to Corona measures.
starting 21.4.2021
- Fields of study:
- WF AI-MA ab 1
WF AI-MA ab 1
- Keywords:
- Virtual Reality, Extended Reality, Augmented Reality
|
| |
Knowledge Discovery in Databases [KDD] -
- Lecturers:
- Richard Lenz, Luciano Melodia
- Details:
- Vorlesung, 2 cred.h, nur Fachstudium
- Dates:
- Tue, 8:15 - 9:45, 00.152-113
Aktueller Hinweis: Diese Veranstaltung findet dieses Semester online statt. Weitere Informationen finden Sie im zugehörigen StudOn-Kurs. Information regarding online courses are provided via StudOn.
- Fields of study:
- WF AI-MA 1
- Prerequisites / Organisational information:
- Konzeptionelle Modellierung
- Contents:
- 1. Introduction
2. Know Your Data
3. Data Preprocessing
4. Mining Frequent Patterns, Associations and Correlations: Basic Concepts and Methods
5. Advanced Frequent Pattern Mining
6. Classification: Basic Concepts
7. Classification: Advanced Methods
8. Cluster Analysis: Basic Concepts and Methods
9. Cluster Analysis: Advanced Methods
10. Outlier Detection
11. Trends and Research Frontiers in Data Mining
- Recommended literature:
- Han, Jiawei ; Kamber, Micheline ; Pei, Jian: Data Mining: Concepts and Techniques. 3rd ed. Waltham, MA : Morgan Kaufmann, 2012 (The Morgan Kaufmann Series in Data Management Systems). - ISBN 978-0-12-381479-1 (copies are available in the TNZB)
Du, Hongbo: Data Mining Techniques and Applications. Andover, UK : Cengage Learning, 2010
Witten, Ian H. ; Frank, Eibe ; Hall, Mark A.: Data Mining. Practical Machine Learning Tools and Techniques. 3rd ed. Burlington, MA : Morgan Kaufmann, 2011 (The Morgan Kaufmann Series in Data Management Systems). - ISBN 978-0-12-3748569-0
- Keywords:
- Data Mining, KDD
|
| |
Virtual Reality in Neuroscience [VRNeuro] -
- Lecturers:
- Daniel Roth, Gastredner, Tutoren
- Details:
- Vorlesung, 2 cred.h, graded certificate, ECTS: 5, nur Fachstudium, Rückfragen, Verständnisfragen, sowie Prüfung können auch auf Deutsch abgelegt werden. --- Questions, comprehension questions, as well as examination can also be taken in German.
- Dates:
- Thu, 13:30 - 15:00, Zoom-Meeting
Neben den regelmäßigen Zoom Meetings wird (je nach Corona Maßnahmen) „Open Lab“ Möglichkeiten unter Einhaltung Corona Maßnahmen geben. --- In addition to regular Zoom meetings, there will be (depending on Corona measures) "Open Lab" opportunities while adhering to Corona measures.
- Fields of study:
- WF AI-MA ab 1
- Keywords:
- Virtual Reality, Neuroscience, Simulation, Human-Computer Interaction
|
|
|
|