machine learning

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

Techniques of machine learning (ML) find a rapidly increasing range of applications touching upon social, economic, and technological aspects of everyday life. They are also being used with great enthusiasm to fill in gaps in our scientific knowledge by data-based modelling approaches. I have followed these developments for a while with interest, concern, and mounting disappointment. When these technologies are employed to take over decisive functionality in safety-critical applications, we would like to exactly know how to guarantee their compliance with pre-defined guardrails and limitations. Moreover, when they are utilized as building blocks in scientific research, it would violate scientific standards -in my opinion- if these building blocks were used without a throrough understanding of their functionality, including inaccuracies, uncertainties, and other pitfalls. In this context, I will juxtapose (a subset of) deep neural network methods with the family of entropy-optimal Sparse Probabilistic Approximation (sSPA) techniques developed recently by Illia Horenko (RPTU Kaiserslautern-Landau) and colleagues.

Prof. Øyvind Breivik (University of Bergen)
The recent advances in ML or AI modelling of the atmosphere and the ocean have upended decades of conventional wisdom - namely that the way forward is higher resolution and better parameterizations of what remains unresolved. Here I will present a handful of examples of how forecasting and modelling the atmosphere and the ocean can be done using graph neural networks and more traditional convolutional neural networks. The big question is then whether we are headed toward a future where models in the traditional sense become obsolete? I will argue that on the contrary, we need the models to guide (supervise) machine learning and artificial intelligence. However, the current use of numerical models is not fit for purpose and we need to rethink what type of numerical models we use for the training. We also need to be aware of the common pitfalls in machine learning - perhaps most importantly how ML models handle previously "unseen" cases, whether these come in the form of extreme weather events or in modelling a future climate very different from what the models have been trained on.

Institutions

• Earth and Society Research Hub (ESRAH) (UHH)

bAIome Center for biomedical AI (UKE) and Bernhard Nocht Institute for Tropical Medicine (BNITM) will host the seminar series entitled “AI in biology and Medicine”. This series aims to capture a broad audience and promote cross institutional collaboration. Our expert speakers will give an overview and insight into particular AI/data science methods being developed in key areas of biology and medicine. We will have drinks and snacks following each seminar to facilitate exchange.

Olga Zolotareva, Institute for Computational Systems Biology, UHH

For further details and hybrid links, please go to the webpage AI in Biology & Medicine