Seminar Humans in the Loop: The Design of Interactive AI Systems (SemHitL)5 ECTS
(englische Bezeichnung: Seminar Humans in the Loop: The Design of Interactive AI Systems)
(Prüfungsordnungsmodul: Seminar Humans in the Loop: The Design of Interactive AI Systems)

Lehrveranstaltungen:

• • Seminar Humans in the Loop: The Design of Interactive AI Systems
    (Seminar, 2 SWS, Bernhard Kainz, Zeit und Raum n.V.)

Empfohlene Voraussetzungen:

Prerequisites recommended:
Deep Learning ML Prof. Dr. Andreas Maier 2+2 5 x E
Pattern Recognition ML Prof. Dr. Andreas Maier 3+1+2 5 x E
Maschinelles Lernen für Zeitreihen ML Prof. Eskofier, Prof. Oliver Amft, Dr. Ch. Mutschler 2+2+2 7.5 x E

Es wird empfohlen, folgende Module zu absolvieren, bevor dieses Modul belegt wird:

Deep Learning (SS 2021)
Pattern Recognition (WS 2020/2021)
Maschinelles Lernen für Zeitreihen (WS 2020/2021)

Inhalt:

Human-in-the-Loop Machine Learning describes processes in which humans and Machine Learning algorithms interact to solve one or more of the following:
Making Machine Learning more accurate Getting Machine Learning to the desired accuracy faster Making humans more accurate Making humans more efficient
Aim of this seminar is to give students insights about state-of-the-art Active Learning and interactive data analysis methods. Students will work independently on specific topics including implementation and analytical components alongside lectures delivered by the course lead, guest lectures and flipped classroom sessions, where students explore a topic independently, which is then discussed in class. Several potential topics will be provided but students are also encouraged to propose their own topics (after discussion with course lead).
Topics covered will include but are not limited to: Introduction to Human-in-the-Loop Machine Learning

• Active Learning Strategies:

• Uncertainty Sampling

• Diversity Sampling

• Other Strategies

Annotating Data for Machine Learning

• Who are the right people to annotate your data?

• Quality control for data annotation

• User interfaces for data annotation

Transfer Learning and Pre-Trained Models

• What are Embeddings?

• What is Transfer Learning?

Adaptive Learning

• Machine-Learning for aiding human annotation

• Advanced Human-in-the-Loop Machine Learning
  

Lernziele und Kompetenzen:

In-depth knowledge of human-n-the-loop machine learning, including deeper insight into current research.
A capability to work independently on application-driven projects. To use a holistic view to critically, independently and creatively identify, formulate and deal with complex issues.
To follow a scientific approach, formulating hypotheses, validation through experimentation and statistical analysis. To plan and use adequate methods to conduct qualified tasks in given frameworks and to evaluate this work. To create, analyse and critically evaluate different technical/architectural solutions.
To integrate knowledge critically and systematically. To clearly present and discuss the conclusions as well as the knowledge and arguments that form the basis for these findings in written and spoken English. A consciousness of the ethical aspects of research and development work.

Literatur:

A specific reading list will be established at the beginning of each term, general literature is listed below:
Quinn J, McEachen J, Fullan M, Gardner M, Drummy M. Dive into deep learning: Tools for engagement. Corwin Press; 2019 Jul 15. https://d2l.ai/
Goodfellow I, Bengio Y, Courville A, Bengio Y. Deep learning. Cambridge: MIT press; 2016 Nov 18. https://www.deeplearningbook.org/
Budd S, Robinson EC, Kainz B. A survey on active learning and human-in-the-loop deep learning for medical image analysis. arXiv preprint arXiv:1910.02923. 2019 Oct 7. https://arxiv.org/abs/1910.02923

Verwendbarkeit des Moduls / Einpassung in den Musterstudienplan:

1. Artificial Intelligence (Master of Science)
   (Po-Vers. 2021s | TechFak | Artificial Intelligence (Master of Science) | Gesamtkonto | Hauptseminar | Seminar Humans in the Loop: The Design of Interactive AI Systems)

Studien-/Prüfungsleistungen:

Seminar Humans in the Loop: The Design of Interactive AI Systems (Prüfungsnummer: 31131)

(englischer Titel: Seminar Humans in the Loop: The Design of Interactive AI Systems)

Prüfungsleistung, Seminarleistung, benotet, 5 ECTS

Anteil an der Berechnung der Modulnote: 100.0 %

weitere Erläuterungen:
Presentation + demo (25 minutes) + written report + working demo and source code. 50% of grade: Presentation + demo (25 minutes) 50% of grade 4 pages IEEE standard paper (excluding references) + code submission.

Prüfungssprache: Englisch

Erstablegung: WS 2021/2022, 1. Wdh.: SS 2022

1. Prüfer:

Bernhard Kainz