Max Planck ETH Center for Learning SystemsAcronym | MPG ETH CLS | Homepage | http://learning-systems.org/ | Country | [nothing] | ZIP, City | | Address | | Phone | | Type | Alliance | Current organization | Max Planck ETH Center for Learning Systems | Members | |
Open OpportunitiesDespite the growing amount of work on applying causal discovery method with expert knowledge to areas of interest, few of them inspect the uncertainty of expert knowledge (what if the expert goes wrong?). This is highly important since that in scientific fields, causal discovery with expert knowledge should be cautious and an approach taking expert uncertainty into account will be more robust to potential bias induced by individuals. Therefore, we aim to develop an iterative causal discovery method with experts in the loop to enable continual interaction and calibration between experts and data.
Based on the qualifications of the candidates, we can arrange a subsidy/allowance for covering traveling or living costs. - Expert Systems, Health Information Systems (incl. Surveillance), Statistics
- Internship, Master Thesis, Semester Project
| This project focuses on developing an explainable Artificial Intelligence (xAI) framework based on graphical modeling (GM), to enhance the capacity and capability of medical AI. Collaborating with the Swiss Paraplegic Centre (SPZ) for validation, our goal is to improve the long-term prognosis of spinal cord injury (SCI) individuals. Through medical records and a multimodal sensory monitoring system, we aim to create digital twins capable of integrating diverse data sources, guiding medical treatment, and addressing common secondary health conditions in the SCI population. The envisioned GM-based digital twin (GMDT) will represent hierarchical relations across demographic features, functional abilities, daily activities, and health conditions for SCI individuals, allowing for downstream tasks such as prediction, causal inference, and counterfactual reasoning. The assimilation and evolution between the physical and digital twins will be implemented under the GM framework, promising advancements in personalized healthcare strategies and improved outcomes for SCI people. Please refer to the attached document for more details about the task description. Based on the candidate's qualifications, funding/allowance can be provided. - Biomedical Engineering, Digital Systems, Knowledge Representation and Machine Learning, Pattern Recognition, Simulation and Modelling
- ETH Zurich (ETHZ), Internship, Master Thesis, Semester Project
| The process of evaluating sleep examinations and diagnosing sleep disorders through polysomnographies (PSGs) is labor-intensive as it requires manual analysis from sleep technicians and doctors. In collaboration with Clinic Barmelweid, a leading sleep and rehabilitation clinic in northwestern Switzerland, we plan to automate this process using machine learning models. Clinic Barmelweid conducts approximately 400-450 PSGs annually and has access to a dataset of more than 5,000 recordings. - Artificial Intelligence and Signal and Image Processing, Biomedical Engineering, Medical and Health Sciences
- Collaboration, ETH Zurich (ETHZ), Internship, Master Thesis, Semester Project
| The Multi-Scale Robotics Lab develops novel actuation methods for endoscopic devices utilizing magnetic navigation systems (MNS). In MNS, an external magnetic field applies forces and torques on magnets attached to the endoscopes. To control these endoscopes, precise shape estimation techniques are required. Current methods try to estimate the endoscope’s shape by measuring the external field along the endoscope using hall-sensors. This method requires precise knowledge about the applied external field and often lacks in localization precision in certain directions.
- Electrical Engineering, Mechanical Engineering
- Master Thesis
| In Formula 1 races, the psychology of human drivers plays a significant role in winning. Who is willing to take more risks and act more aggressively to secure victory? In this project, we aim to replicate such edge scenarios in autonomous racing. Until now, autonomous race cars often act conservatively, assuming the opponent's trajectory is fixed and not pushing to the limits of their constraints. Using game-theoretic control, we want to model the strategic, risky decision-making that happens on the race track. Specifically, we will delve into the competitive behaviors emerging from feedback Nash Equilibria (NE) and open-loop NE and explore whether we can encourage agents to be more aggressive with one solution concept over the other. Can we demonstrate the superiority of feedback equilibria theoretically and in simulation? - Intelligent Robotics, Robotics and Mechatronics, Systems Theory and Control, Systems Theory and Control
- ETH Zurich (ETHZ), Master Thesis, Semester Project
| We currently want to (i) elaborate the added value of a campus board that records the forces per limb, (ii) determine grasping phases for kinematic analyses of the phalanges more pragmatically than with 6DoF sensors, and (iii) drive forward a competition analysis based purely on video material. - Biomedical Engineering, Human Movement and Sports Science
- Internship, Semester Project
| Estimating human poses within global trajectories is critical for applications such as augmented reality and sports analytics, yet it often demands precisely calibrated cameras and significant computational efforts. With advancements in deep learning and pose estimation technologies, various models can be trained using 2D or 3D motion data. However, effectively integrating these models to predict and analyze human movement trajectories in a continuous and dynamic environment remains challenging. This project aims to create a robust system that estimates and predicts human poses accurately, facilitating advancements in dynamic pose analysis and real-world applications. - Information, Computing and Communication Sciences
- ETH Zurich (ETHZ), Lab Practice, Master Thesis, Semester Project
| Reaching and grasping an object of interest is a relatively simple
task that can be achieved robustly in case the object is equipped
with a simple handle and a visual marker. However, often the difficulty in the task originates from the rest of the environment.
The object may be placed in cluttered spaces with diverse obstacles
as well as dynamic entities, e.g. humans, other robots. As a result,
executing the task of reaching and grasping the object necessitates
collision-free motion control capabilities. - Intelligent Robotics, Robotics and Mechatronics
- Master Thesis, Semester Project
| This thesis aims to utilize deep learning techniques to analyze eye-tracking data during a goal-directed upper limb task, particularly focusing on participants under the influence of alcohol. The objective is to develop digital health metrics that can elucidate differences in movement planning. - Engineering and Technology, Information, Computing and Communication Sciences, Medical and Health Sciences
- Bachelor Thesis, Master Thesis, Semester Project
| The field of image restoration is continually evolving with the introduction of advanced deep learning models capable of tackling increasingly complex restoration tasks. The use of foundation models, which are pre-trained on diverse data before being fine-tuned for specific tasks, has demonstrated considerable promise in various domains of artificial intelligence. This proposal aims to develop a new foundation model for image restoration by incorporating the state-space model and enhancing it with text prompt capabilities. This approach will allow the model to perform targeted restorations based on descriptive textual prompts, significantly improving the precision and quality of the restoration process. - Computer Vision
- Collaboration, ETH for Development (ETH4D) (ETHZ), Master Thesis
|
|