|
Einrichtungen >> Technische Fakultät (TF) >> Department Informatik (INF) >>
|
Lehrstuhl für Informatik 5 (Mustererkennung)
|
Cognitive Neuroscience for AI Developers [CNAID(A)] -
- Dozentinnen/Dozenten:
- Patrick Krauß, Andreas Kist, Andreas Maier
- Angaben:
- Vorlesung, 4 SWS, ECTS: 5, nur Fachstudium
- Termine:
- Mi, 10:15 - 11:45, H9
Do, 14:15 - 15:45, HG
- Studienrichtungen / Studienfächer:
- WPF MT-BA ab 5
WPF IuK-MA-MMS-INF ab 1
WPF ICT-MA-MPS ab 1
WPF INF-MA ab 1
WPF INF-BA-V-ME ab 1
WPF MT-MA-BDV ab 1
WPF AI-MA ab 1
- Voraussetzungen / Organisatorisches:
- FAU students register for the written exam via meinCampus.
https://www.studon.fau.de/crs3690005.html
- Inhalt:
- 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.
(automatisch geplant, erwartete Hörerzahl original: 200, fixe Veranstaltung: nein)
- Empfohlene Literatur:
- 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.
|
|
Deep Learning [DL(A)] -
- Dozent/in:
- Andreas Maier
- Angaben:
- Vorlesung, 2 SWS, ECTS: 2,5, nur Fachstudium, für FAU Scientia Gaststudierende zugelassen, Information regarding the online teaching will be added to the studon course
- Termine:
- Mi, 14:15 - 15:45, H7
- Studienrichtungen / Studienfächer:
- WPF ME-BA-MG6 4-6
WPF INF-MA ab 1
WPF MT-MA-BDV 1
WPF ME-MA-MG6 4-6
- Voraussetzungen / Organisatorisches:
- The following lectures are recommended:
Application via https://www.studon.fau.de/crs3888652.html
- Inhalt:
- 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.
(automatisch geplant, erwartete Hörerzahl original: 350, fixe Veranstaltung: nein)
- Empfohlene Literatur:
- 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)
- Schlagwörter:
- deep learning; machine learning
|
|
Deep Learning for Beginners (VHB-Kurs) -
- Dozentinnen/Dozenten:
- Aline Sindel, Andreas Maier
- Angaben:
- Vorlesung, 2 SWS, ECTS: 2,5, für FAU Scientia Gaststudierende zugelassen
- Termine:
- Zeit/Ort n.V.
- Studienrichtungen / Studienfächer:
- WPF INF-BA ab 3
WF MT-BA ab 3
WPF DS-BA ab 3
- Voraussetzungen / Organisatorisches:
- Requirements: mathematics for engineering, basic knowledge of python
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.
- Inhalt:
- Neural networks have had an enormous impact on research in image and signal processing in recent years. In this course, you will learn all the basics about deep learning in order to understand how neural network systems are built. The course is addressed to students who are new to the field. In the beginning of the course, we introduce you to the topic with some applications of deep learning in the field of medical imaging, digital humanities and industry projects. Before we dive into the core elements of neural networks, there are two lecture units on the fundamentals of signal and image processing to teach you relevant parts of system theory such as convolutions, Fourier transform, and sampling theorem. In the next lecture units, you learn the basic blocks of neural networks, such as backpropagation, fully connected layers, convolutional layers, activation functions, loss functions, optimization, and regularization strategies. Then, we look into common practices for training and evaluating neural networks. The next lecture unit is focusing on common neural network architectures, such as LeNet, Alexnet, and VGG. It follows a lecture unit about unsupervised learning that contains the principles of autoencoders and generative adversarial networks. Lastly, we cover some applications of deep learning in segmentation and object detection.
The accompanying programming exercises will provide a deeper understanding of the workings and architecture of neural networks, in which you will develop a basic neural network from scratch in pure Python without using deep learning frameworks, such as PyTorch or TensorFlow.
At the end of the semester, there will be a written exam.
(erwartete Hörerzahl original: 250, fixe Veranstaltung: nein)
|
|
Kolloquium Magnetic Resonance Imaging [MRI] -
- Dozentinnen/Dozenten:
- Andreas Maier, Armin Nagel, Frederik Laun, , Sebastian Bickelhaupt, Daniel Giese, Florian Knoll
- Angaben:
- Kolloquium, 2 SWS, Das Kolloquium findet als Online-Veranstaltung statt. Zeit: Do 17:00 – 18:30 Uhr.
- Termine:
- Do, 17:00 - 18:30, Raum n.V.
- Studienrichtungen / Studienfächer:
- WPF INF-MA ab 1
- Schlagwörter:
- magnetic resonance imaging, mri
|
|
Mainframe Programmierung I -
- Dozent/in:
- Sebastian Wind
- Angaben:
- Vorlesung mit Übung, ECTS: 5, für FAU Scientia Gaststudierende zugelassen
- Termine:
- Online-Kurs im StudOn
- Studienrichtungen / Studienfächer:
- WF INF-MA ab 1
- Voraussetzungen / Organisatorisches:
- * Der Kurs wird als Online-Kurs bei der VHB im StudOn im betreuten Selbststudium angeboten. *
Anrechenbar für die Säulen:
softwareorientiert
anwendungsorientiert
- Inhalt:
- Der Begriff "Mainframe" bezeichnet grosse Rechenanlage, wie sie in der Wirtschaft für extrem grossen Anwendungen eingesetzt werden. Typische Branchen sind Banken und Versicherungen, aber auch Automobilhersteller und AI-Anwender.
Der Online-Kurs soll nun die Möglichkeit eröffnen, Erfahrungen mit der Programmierung eines Mainframes zu sammeln. Dazu gehören die elementaren Programmieraufgaben wie editieren, übersetzen, binden, laden, ausführen und debuggen, die anhand von Beispielen in der Programmiersprache CoBOL geübt werden.
Die Architektur der Mainframes werden sowohl aus Sicht der Rechnerarchitektur wie auch der Anwendersicht beleuchtet. Insbesondere werden die Virtualisierungsmöglichkeiten udn die gängigen Betriebssysteme wie z/OS und Linux auf den Mainframes behandelt.
Den Abschluss und Ausblick bildet die Datenhaltung und die Integration in die IT-Systemlandschaft.Inhalt:
0. Begrüßung und Einführung
1. CoBOL Programmierung
2. Einführung Mainframes
3. IBM Mainframe Architektur
4. z/OS
5. Anwendungsprogrammierung
6. Virtualisierung
7. Linux
8. Integration in die IT-Systemlandschaft (erwartete Hörerzahl original: 60, fixe Veranstaltung: nein)
- Empfohlene Literatur:
- Wird über StudOn zur Verfügung gestellt.
- Schlagwörter:
- Mainframe, Programmierung, Cobol, Fortran, z, zOS, CICS, REXX, Rational
|
|
Mainframe Programmierung II -
- Dozent/in:
- Sebastian Wind
- Angaben:
- Vorlesung mit Übung, 4 SWS, ECTS: 5, Online-Kurs
- Termine:
- Online-Kurs der VHB
- Studienrichtungen / Studienfächer:
- WF INF-BA-V-PS ab 4
WF INF-MA 1
- Voraussetzungen / Organisatorisches:
- * Der Kurs wird als Online-Kurs bei der VHB im StudOn im betreuten Selbststudium angeboten. *
Anrechenbar für die Säulen:
softwareorientiert
anwendungsorientiert
- Inhalt:
- Aufbauend auf dem Modul Mainframe Programmierung I werden in diesem Kurs die Themen Virtualisierung, Online Transaction Processing und die Anwendung von Datenbanken behandelt. Darüber hinaus werden erweiterte Cobol Konzepte beleuchtet und die Anwendung der Skriptsprache JCL vermittelt. Der Kurs Mainframe Programmierung II wird online abgehalten und bietet den Studierenden die Möglichkeit sich durch Selbststudium neue Kompetenzen anzueignen, sowie das neu gewonnene Wissen anhand von Screencasts einzuüben.
Lern- bzw. Methodenkompetenz
Das Modul vermittelt sowohl Kompetenzen im selbst organisierten Lernen, wie auch Erfahrungen mit einer multi-modalen Lernumgebung.
(erwartete Hörerzahl original: 12, fixe Veranstaltung: nein)
- Schlagwörter:
- Mainframe, Programmierung, Programming, Unternehmensdatenverarbeitung, Enterprise Computing
|
|
Medical Image Processing for Diagnostic Applications (VHB-Kurs) -
- Dozentinnen/Dozenten:
- Andreas Maier, Luis Carlos Rivera Monroy, Celia Martín Vicario, Manuela Meier, Arpitha Ravi
- Angaben:
- Vorlesung, 4 SWS, ECTS: 5
- Termine:
- Zeit/Ort n.V.
- Studienrichtungen / Studienfächer:
- WPF INF-MA ab 1
WPF INF-BA-V-ME ab 5
PF CE-MA-TA-IT ab 1
WPF IuK-MA-MMS-INF ab 1
WPF ICT-MA-MPS 1-4
WPF MT-MA-BDV ab 1
WPF MT-BA ab 5
WF CME-MA 1-4
WPF AI-MA ab 1
- Voraussetzungen / Organisatorisches:
- 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.
- Inhalt:
- 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.
(erwartete Hörerzahl original: 100, fixe Veranstaltung: nein)
- Schlagwörter:
- Mustererkennung, Medizinische Bildverarbeitung
|
|
Medical Image Processing for Interventional Applications (VHB-Kurs) -
- Dozentinnen/Dozenten:
- Andreas Maier, Luis Carlos Rivera Monroy, Celia Martín Vicario, Manuela Meier, Arpitha Ravi
- Angaben:
- Vorlesung, 4 SWS, ECTS: 5
- Termine:
- Zeit/Ort n.V.
- Studienrichtungen / Studienfächer:
- WPF MT-BA ab 5
WPF INF-BA-V-ME 4-6
WPF INF-MA 1-4
WPF IuK-MA-MMS-INF 1-3
WPF ICT-MA-MPS 1-4
WF CE-MA-INF ab 1
WPF MT-MA-BDV 1-2
WPF AI-MA ab 1
- Voraussetzungen / Organisatorisches:
- mathematics for engineering; This lecture focuses on interventional procedures. It is recommended but not necessary to attend Medical Image Processing for Diagnostic Applications (MIPDA) before.
- Inhalt:
- This lecture focuses on recent developments in image processing driven by medical applications. All algorithms are motivated by practical problems. The mathematical tools required to solve the considered image processing tasks will be introduced.
In addition to the lectures, we also offer exercise classes. The exercises consist of theoretical parts where you immerse in lecture topics. But we also set emphasis on the practical implementation of the methods.
(erwartete Hörerzahl original: 100, fixe Veranstaltung: nein)
- Schlagwörter:
- Mustererkennung, Medizinische Informatik, Medizinische Bildverarbeitung
|
|
Pattern Recognition [PR(A)] -
- Dozentinnen/Dozenten:
- Andreas Maier, Paul Stöwer
- Angaben:
- Vorlesung, 3 SWS, Schein, ECTS: 3,75, geeignet als Schlüsselqualifikation, This class will be given purely on fau.tv. Short videos will be posted on a regular schedule (not necessary the in-person time mentioned here at UnivIs)
- Termine:
- Mo, 14:15 - 15:45, H4
Di, 08:15 - 09:45, H4
- Studienrichtungen / Studienfächer:
- WPF ME-BA-MG6 3-5
WPF MT-MA-BDV 1-3
PF IuK-MA-MMS-INF ab 1
PF ICT-MA-MPS 1-4
WPF CE-MA-INF ab 1
WF CE-BA-TW ab 5
WPF INF-MA ab 1
WPF CME-MA ab 1
WF ASC-MA 1-4
WPF ME-MA-MG6 1-3
WPF DS-MA ab 1
- Schlagwörter:
- Mustererkennung, maschinelle Klassifikation
|
|
Projekt Computer Vision [ProjCV(RZ)] -
- Dozentinnen/Dozenten:
- Vincent Christlein, Martin Mayr
- Angaben:
- Praktikum, ECTS: 10, 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
- Termine:
- Mo, 12:00 - 14:00, Übung 3 / 01.252-128, 00.156-113 CIP
- Studienrichtungen / Studienfächer:
- WPF INF-MA ab 1
WPF MT-MA ab 1
- Voraussetzungen / Organisatorisches:
- Basic knowledge of image processing is desirable. In the first session there will be a short recap on image representation and basic image filtering techniques. However, having visited lectures such as Introduction to Pattern Recognition (IntroPR) or Diagnostic Medical Image Processing (DMIP) might prove beneficial.
Please contact us if you have any questions. You can register via Studon (https://www.studon.fau.de/crs4040713.html) for the Computer Vision Project. During the semester lecture and exercise alternate on a weekly basis. Exercises are supervised and take place in one of the CIP pools. All exercises must be completed. You can get either 5 or 10 ECTS credits for this project. The following options are available:
5 ECTS (counts as: Hochschulpraktikum)
This option requires:
lectures (strongly recommended as they introduce the background required for the exercises)
exercises (in groups of 2 people) need to be finished on time
individual presentation about a state-of-the-art research paper at the end of the semester (graded if needed)
10 ECTS (counts as Hochschulpraktikum (5 ECTS) + Forschungspraktikum (5 ECTS), or Master Project Computer Science (10 ECTS))
lectures (strongly recommended as they introduce the background required for the exercises)
exercises (in groups of 2 people) need to be finished on time
individual coding/research project under supervision of a LME PhD student at the end of regular schedule (graded if needed)
Important: You cannot use the lecture/exercise part as a 5 ECTS research project (Forschungspraktikum). Please contact one of the PhD students at the lab if you need a research project.
- Inhalt:
- This project gives you the chance to learn about current computer vision topics and get practical experience in the field during the exercises.
Last semester, the following topics were covered:
(erwartete Hörerzahl original: 10, fixe Veranstaltung: nein)
- Schlagwörter:
- Master Project, Pattern Recognition, Computer Vision
|
|
Seminar Advanced Deep Learning [SemADL] -
- Dozentinnen/Dozenten:
- Katharina Breininger, Vincent Christlein, Andreas Maier
- Angaben:
- Seminar, 2 SWS, ECTS: 5, nur Fachstudium, The first session of the semester will an online meeting, subsequent meetings will be in person.
- Termine:
- Di, 12:00 - 14:00, Seminarraum ZMPT
- Studienrichtungen / Studienfächer:
- WPF INF-MA ab 1
WPF MT-MA-BDV ab 1
WPF CE-MA-TA-MT ab 1
- Voraussetzungen / Organisatorisches:
- Registration via StudOn:
https://www.studon.fau.de/crs4006742.html
https://www.studon.uni-erlangen.de/univis_2022s.Lecture.21733718
- Inhalt:
- Deep Learning-based algorithms showed great performance in many fields of image processing and pattern recognition and compete with technologies such as compressive sensing and iterative optimization. The basis for the success of these algorithms is the availability of large amounts of data (big data) for training and of high computing power (typically GPUs).
In this seminar we try to explore advanced deep learning methods. In particular, we will aim to develop a deeper understanding of certain topics, for example: graph neural networks, unsupervised learning, differentiable learning, invertible learning, neural ordinary differential equations, transfer learning, multi-task learning, uncertainty DL, etc.
- Schlagwörter:
- algorithms; medical image processing
|
|
Seminar – Road Scene Understanding for the Visually Impaired [SemRSUVI] -
- Dozentinnen/Dozenten:
- Hakan Calim, Andreas Maier
- Angaben:
- Seminar, 2 SWS, ECTS: 5
- Termine:
- Fr, 8:15 - 9:30, 09.150
- Inhalt:
- Understanding road scenes and creating maps from urban environments is a challenging task in Computer Vision. It is used in self-driving cars, robotics and assistive navigation systems for blind or visually impaired pedestrians.
The topic of this seminar will be to build a software tools that will enable the creation of a navigation assistant for the blind and visually impaired. In particular the following issues will be addressed:
1. Define the hardware resources (e.g. computational resources, camera/cell phone, TOF/Lidar/focal length, sensors, ...)
2. Set up a web-based collaborative labeling environment using crowd-based labeling tools (e.g. EXACT (https://github.com/ChristianMarzahl/Exact))
3. define guidelines for crowdsourced labeling
4. Define use cases (face recognition, license plates) for managing and anonymizing the data.
The aim of this project seminar is to build tools that will enable preparation of data, e.g. image segmentation of roads, sidewalks and obstacles, etc. In a second step, the data should be ready for the creation of maps and respective annotations from the scenes so it can be used building for an assistive navigation system for blind or visually impaired pedestrians.
- Empfohlene Literatur:
- J. C. Chang, S. Amershi, E. Kamar, Revolt: Collaborative Crowdsourcing for Labeling Machine Learning Datasets, CHI 2017, Denver, CO, USA, May 6-11, 2017, http://library.usc.edu.ph/ACM/CHI%202017/1proc/p2334.pdf
Oana Inel, Khalid Khamkham, Tatiana Cristea et al., CrowdTruth: Machine-Human Computation Framework for Harnessing Disagreement in Gathering Annotated Data, International Semantic Web Conference, ISWC 2014: The Semantic Web - ISWC 2014, pp 486 504, https://link.springer.com/chapter/10.1007/978-3-319-11915-1_31
Brody Huval, Tao Wang, Sameep Tandon et al., An Empirical Evaluation of Deep Learning on Highway Driving, Cornell University, Apr. 7, 2015, https://arxiv.org/abs/1504.01716
Joel Pazhayampallil, Free Space Detection with Deep Nets for Autonomous Driving, http://cs231n.stanford.edu/reports/2015/pdfs/jpazhaya_final.pdf
|
|
Voice-enabled healthcare [VEH] -
- Dozent/in:
- Björn Heismann
- Angaben:
- Seminar, ECTS: 2,5, nur Fachstudium
- Termine:
- Di, 14:15 - 15:45, Seminarraum ZMPT
Further information will be provided on StudOn
- Studienrichtungen / Studienfächer:
- WPF MT-MA ab 1
- Voraussetzungen / Organisatorisches:
- Master-Studenten MT Semester 1-3 (und andere interessierte Fachrichtungen)
- Inhalt:
- Voice recognition, speech synthesis, sentiment analysis and natural language processing are groundbreaking technologies for improved human machine interactions. This seminar intends to give students the opportunity to get in touch with the latest technologies in this space and venture out on a literature review or prototype building journey to improve healthcare applications. The seminar features a lecture part where participants are introduced to the algorithmic background of voice and natural language processing. You are enabled to analyze literature and / or develop own prototypes of voice-enabled healthcare applications. Potential fields of application include e.g. voice-controlled interventional devices and sentiment analysis for psychiatric diseases.
Objectives:
Understand science of voice recognition and natural language processing
Understand medical human interactions and medical needs
Analyze combinations of voice technologies and potential applications in medicine
Skills:
Algorithmic background of voice recognition and NLP
Literature analysis and prototype building
Advanced knowledge: Medical technology
Basic knowledge: Medicine
|
|
|
|
|
UnivIS ist ein Produkt der Config eG, Buckenhof |
|
|