interdisciplinary research

The presentation series “Train your engineering network” on diverse topics of Machine Learning addresses all interested persons at TUHH, from MLE partners as well as from the Hamburg region in general and aims at promoting the exchange of information and knowledge between these persons as well as their networking in a relaxed atmosphere. Thereby, the machine learning activities within MLE, TUHH and in the wider environment shall be made more visible, cooperations shall be promoted and also interested students shall be given an insight.

Sören Laue

Most problems from classical machine learning can be cast as an optimization problem. I will present GENO (GENeric Optimization), a framework that lets the user specify a constrained or unconstrained optimization problem in an easy-to-read modeling language. GENO then generates a solver that can solve this class of optimization problems. The generated solver is usually as fast as hand-written, problem-specific, and well-engineered solvers. Often the solvers generated by GENO are faster by a large margin compared to recently developed solvers that are tailored to a specific problem class. I will dig into some of the algorithmic details, e.g., computing derivatives of matrix and tensor expressions, the optimization methods used in GENO, and their implementation in Python.

All talks will be streamed via Zoom using https://tuhh.zoom.us/j/85203195489?pwd=K21saVMvZHc0d2NoNHd2bDZ6TmdDUT09
Meeting-ID: 852 0319 5489
Code: 827469

The presentation series “Train your engineering network” on diverse topics of Machine Learning addresses all interested persons at TUHH, from MLE partners as well as from the Hamburg region in general and aims at promoting the exchange of information and knowledge between these persons as well as their networking in a relaxed atmosphere. Thereby, the machine learning activities within MLE, TUHH and in the wider environment shall be made more visible, cooperations shall be promoted and also interested students shall be given an insight.

Johanna Gleichauf

The monitoring of vital signs and increasing patient comfort are cornerstones of modern neonatal intensive care. Commonly used monitoring methods are based on skin contact which can cause irritations and discomfort in preterm neonates. Therefore, non-contact approaches are the subject of current research aiming to resolve this dichotomy. Robust neonatal face detection is essential for the reliable detection of heart rate, respiratory rate and body temperature. While solutions for adult face detection are established, the unique neonatal proportions require a tailored approach. Additionally, sufficient open-source data of neonates on the NICU is lacking. We set out to train neural networks with the thermal-RGB-fusion data of neonates. We propose a novel indirect fusion approach including the sensor fusion of a thermal and RGB camera based on a 3D time-of-flight (ToF) camera. Unlike other approaches, this method is tailored for close distances encountered in neonatal incubators. Two neural networks were used with the fusion data and compared to RGB and thermal networks. For the class “head” we reached average precision values of 0.9958 (RetinaNet) and 0.9455 (YOLOv3) for the fusion data. Compared with the literature, similar precision was achieved, but we are the first to train a neural network with fusion data of neonates. The advantage of this approach is in calculating the detection area directly from the fusion image for the RGB and thermal modality. This increases data efficiency by 66%. Our results will facilitate the future development of non-contact monitoring to further improve the standard of care for preterm neonates.

All talks will be streamed via Zoom
Meeting-ID: 852 0319 5489
Code: 827469

The presentation series “Train your engineering network” on diverse topics of Machine Learning addresses all interested persons at TUHH, from MLE partners as well as from the Hamburg region in general and aims at promoting the exchange of information and knowledge between these persons as well as their networking in a relaxed atmosphere. Thereby, the machine learning activities within MLE, TUHH and in the wider environment shall be made more visible, cooperations shall be promoted and also interested students shall be given an insight.

Marcus Venzke 

The talk presents a new technique for unsupervised learning of repeatedly occurring process states from a suite of time series derived from preprocessed sensor data recorded from a fixed process. As a first application we consider the process of moving a good along a path in an industrial environment. The goal is to identify individual sections of the path while they are being traversed. The technique determines thresholds in time series leading to the same succession of increasing and decreasing intersections for all paths of the training data. The trained model is a so-called “threshold tree”. It consists of thresholds for the different time series splitting a path into its sections to be recognized. The execution of threshold trees has a low CPU and memory footprint allowing their use on micro-controllers, e.g. in embedded systems. Due to their intuitive comprehensibility "threshold trees" belong to the category of explainable AI.

All talks will be streamed via Zoom using https://tuhh.zoom.us/j/85203195489?pwd=K21saVMvZHc0d2NoNHd2bDZ6TmdDUT09
Meeting-ID: 852 0319 5489
Code: 827469

Es besteht ein immer größer werdender Bedarf an Videoinhalten und Video-Formaten für die unterschiedlichsten Distributionskanäle.

Bildoptimierung, Nachbearbeitung, Text-to-Video, Videotranskription, Übersetzungen und Untertitelerstellung sind dabei einige der zentralen Anforderungen an die Produktion und Postproduktion. Zeit- und kostenintensive, physische Dreharbeiten und tagelange Nachbearbeitung werden hingegen immer weniger nötig sein, um Videos mit hoher Skalierbarkeit zu erstellen.

Ist es jetzt schon möglich, Videos ohne Profi-Kenntnisse, allein durch Texteingabe auf KI-Generatoren- und Plattformen Videoinhalte zu erzeugen?

Wie können zukünftige Videoproduktionsprozesse skaliert und optimiert werden?
Inwieweit ist eine Automatisierung von Abläufen in der Videoproduktion sinnvoll?

Und wie groß sind die Effizienzpotenziale in der Anwendung von KI-Generatoren hinsichtlich der Produktionskosten, des zeitlichen Aufwands und der Komplexität? 
In dieser Online-Schulung werden KI-Generatoren für die Optimierung der Videoproduktion vorgestellt.

Anmeldung hier

Als virtuellen Lernort werden wir ZOOM nutzen. Der ZOOM-Link wird einen Tag vor Schulungsbeginn bis 13:00 Uhr versendet.

Dr. Susanne Draheim, Department Informatik, HAW Hamburg

Öffentliche Vorträge im Allgemeinen Vorlesungswesen Ringvorlesung: Künstliche Intelligenz zwischen Handlungsmacht und gesellschaftlichen Gestaltungsbedarfen
Informatik und Sozial-/Kulturwissenschaft im Gespräch

Darstellungen der KI in den Medien aber auch in der Politik und Wissenschaftsförderung oszillieren zwischen Schrecken, Verheißung und Notwendigkeit, vielfach ohne dass ein hinreichendes informatisches Grundverständnis besteht und informierte Entscheidungen oder Umgangsweisen mit KI-Technologien ermöglicht. Neuere Projekte zwischen Forschung und Wissenschaftskommunikation, wie etwa das "KI-Observatorium", setzen deswegen auf Wissensvermittlung und -austausch.

Das Kolloquium folgt einem ähnlichen Anliegen, das Wissen über KI-Technologien zu erweitern und dabei ein besseres Verständnis davon zu entwickeln, wie sich Handlungsmacht und -möglichkeiten durch die KI neu gestalten. Indem es interdisziplinäre Gespräche zwischen Kulturwissenschaftler*innen und Informatiker*innen initiiert, werden in kurzen Vorträgen historische und theoretische Grundlagen, sowie ausgewählte Anwendungsbereiche der Künstlichen Intelligenz vorgestellt und diskutiert. Anhand von Praxisbeispielen von KI in Anwendung und Entwicklung werden KI Technologie verständlich und für die Analyse greifbar. Das hauptsächliche Ziel des Kolloquiums besteht in beiden Disziplinen darin, die jeweils andersartige Herangehensweise kennen und verstehen zu lernen.

Institutions

• HAW Hamburg
• Universität Hamburg