ETH Competence Center - ETH AI Center| Acronym | | | Homepage | https://ai.ethz.ch/ | | Country | Switzerland | | ZIP, City | | | Address | | | Phone | | | Type | Academy | | Parent organization | ETH Zurich | | Current organization | ETH Competence Center - ETH AI Center | | Members | |
Open OpportunitiesHave you ever wondered how the brain works? How does it change to store new memories? How do neurons exactly evolve to help us think? As you might have guessed, these are not easy questions. A way to explore possible answers is to analyze neural data. If you want to use your computational skills to solve a part of the brain mystery, this project could be something for you. - Biology, Information, Computing and Communication Sciences, Mathematical Sciences, Physics
- Master Thesis, Semester Project
| This project is motivated by the emerging potential of digital biomarkers derived from passive sensing data to assess and characterize disease characteristics. Widespread wearables and smartwatches enable non-invasive, passive, objective, and continuous measurement of physical activity throughout 24 hours. Combined with cutting-edge ML/AI approaches, this 24-hour passive sensing data may reveal distinct physical activity profiles associated with illnesses, which can be used for the classification of different types of diseases. Distinct physical activity profiles may represent different manifestations of the health states including circadian rest-activity rhythm among diseases. To this end, we aim to conduct retrospective data analysis to conduct an in-depth investigation of wearable-based physical activity data by varying resolutions and build ML/AI models for disease classifications. - Engineering and Technology, Information, Computing and Communication Sciences, Mathematical Sciences, Medical and Health Sciences
- Master Thesis
| This Master's Thesis Project involves research and development of novel Machine Learning techniques for Representation Learning of a scene from multiple view points, for the purpose of Robotic Manipulation. - Computer Vision, Intelligent Robotics
- Master Thesis
| Large language models trained on huge collections of text have achieved state-of-the-art performance across many NLP tasks. However, there is no systematic way to control the text that is generated by such models. The control aspect is specifically important when it comes to developing such models safely for real-world applications, e.g., to make sure that the generations are non-toxic and factual. For this reason, there has been a wide variety of methods proposed in the literature recently for controlled generation. The goal of this project is to do a systematic analysis of such methods across different tasks and metrics. - Text Processing
- Master Thesis
| We aim to develop a method for large-scale pre-training and fine-tuning of a Robotic Transformer model for dexterous human hand control. - Intelligent Robotics, Neural Networks, Genetic Alogrithms and Fuzzy Logic
- Bachelor Thesis, Master Thesis
| Graph neural networks (GNNs) have attracted intense interest recently, and so does their explainability. AI can help solve major challenges in environmental sciences, one of them being radiation level forecast and understanding. While many methods using ML techniques and deep neural networks are already used for climate sciences, the power of graph neural networks is still under estimated in climate applications. Radiation is a key component of the Earth’s energy cycle. Convergence of radiative flux is a heat source and an essential component of the numerical solver of the thermodynamic equation in a climate model. The current problem that scientists face is the problem of discontinuity of predicted radiation levels due to the space discretization. The radiative flux obtained from deep learning methods is often not smooth enough to obtain realistic heating rates. Currently, the heating rates are obtained from the radiative flux by a simple vertical finite-difference differentiation to estimate the vertical flux convergence. GNNs are promising tools to predict continuous radiation flow in the atmosphere and from that heating rates. A particular advantage of ML-based methods is their resource efficiency, which has the potential to considerably reduce the compute resources needed for a complete climate integration and allow for high model resolution that is needed to accurately simulate high-impact weather.
- Atmospheric Sciences, Computer Vision
- Master Thesis
| Augmented Reality (AR) devices find their into a variety of enterprise use cases with increasing frequency and are often used to simplify and improve existing workflows. A majority of these use cases attach virtual content to real world environments, to static or even moving objects, but others require highly accurate relative poses between two or more markers to benefit the user.
AR applications already use fiducial markers (i.e April Tags) for such scenarios for many years. Markers are detected and identified in a camera image using a detector and then based on its geometry and features the marker's 3D pose is estimated. To achieve higher accuracy, algorithms can apply several refinement methods to minimize the pose error.
However high-accuracy applications often require more reliability, precision and update frequency than conventional markers can provide and the deployment of external navigation systems that fulfill these requirements is often very costly and come with their own downsides and limitations. - Computer Vision, Simulation and Modelling, Virtual Reality and Related Simulation
- Master Thesis
|
|
