University of Zurich

Open Opportunities

Electrical Flow-Based Graph Embeddings for Event-based Vision and other downstream tasks University of Zurich Robotics and Perception This project explores a novel approach to graph embeddings using electrical flow computations. Artificial Intelligence and Signal and Image Processing, Knowledge Representation and Machine Learning, Mathematics Master Thesis

High-speed Time-Correlated Single Photon Counting for Brain Imaging in Freely Moving Mice ETH Zurich Functional and Molecular Imaging We are looking for motivated students for a semester project, master thesis, or internship that will focus on the programming tasks related to data acquisition and processing from state-of-the-art FPGA-based photon counting electronics and real-time processing and visualization of microscopy images. Biomedical Engineering, Biosensor Technologies, Electrical and Electronic Engineering, Engineering/Technology Instrumentation, Interdisciplinary Engineering ETH Zurich (ETHZ), Internship, Master Thesis, Semester Project, Student Assistant / HiWi

Leveraging Long Sequence Modeling for Drone Racing University of Zurich Robotics and Perception Study the application of Long Sequence Modeling techniques within Reinforcement Learning (RL) to improve autonomous drone racing capabilities. Engineering and Technology, Information, Computing and Communication Sciences Master Thesis

Neural Architecture Knowledge Transfer for Event-based Vision University of Zurich Robotics and Perception Perform knowledge distillation from Transformers to more energy-efficient neural network architectures for Event-based Vision. Engineering and Technology, Information, Computing and Communication Sciences Master Thesis

Hybrid Spiking-Deep Neural Network System for Efficient Event-Based Vision Processing University of Zurich Robotics and Perception Master's thesis in collaboration with SynSense: Neuromorphic Intelligence & Application Solutions Artificial Intelligence and Signal and Image Processing, Dynamical Systems Master Thesis

Enhancing tree species identification using multi-view Convolutional Neural Networks ETH Zurich Forest Resources Management Other organizations: EcoVision Lab Tree species identification is crucial for biodiversity monitoring, forest management, and understanding ecological processes. Advances in computer vision and deep learning have enabled the use of multi-view convolutional neural networks (CNNs) to classify species by integrating complementary information from different views. This thesis explores the integration of multi-view data and citizen science images to develop a scalable, high-accuracy tree species identification framework. By addressing challenges related to data variability and leveraging diverse georeferenced plant images, the study aims to enhance the training and generalization of multi-view CNN models. Computer Vision, Forestry Sciences, Photogrammetry and Remote Sensing Master Thesis

Learning Robust Agile Flight via Adaptive Curriculum University of Zurich Robotics and Perception This project focuses on developing robust reinforcement learning controllers for agile drone navigation using adaptive curricula. Commonly, these controllers are trained with a static, pre-defined curriculum. The goal is to develop a dynamic, adaptive curriculum that evolves online based on the agents' performance to increase the robustness of the controllers. Engineering and Technology Master Thesis, Semester Project

Interventional ML for respiratory failure prediction and prevention University of Zurich Institut für Intensivmedizin Acute Respiratory Distress Syndrome (ARDS) is a life-threatening condition with high mortality rates in intensive care units, making early prediction crucial for timely interventions. This project explores Bayesian networks as an interpretable alternative to traditional machine learning models for ARDS risk prediction. By leveraging counterfactual explanations and interventional machine learning, we aim to identify actionable ventilator settings that could reduce ARDS risk. The analysis will use real-world ICU data from the University Hospital of Zurich and be externally validated on public datasets. This work bridges AI, causal inference, and clinical decision-making to enhance patient care. Clinical Engineering, Medical and Health Sciences Course Project, Master Thesis, Semester Project

Characterization of an advanced high-speed SICM for live cell imaging ETH Zurich Biosensors and Bioelectronics (LBB) Scanning ion conductance microscopy (SICM) is the non-​contact SPM technology to image live cells based on glass capillaries with a nanometric aperture. It applies a voltage and measures the ionic current flowing through the pipette above the sample in the buffer solution: the recorded current represents the feedback signal to measure the topography of the sample. This project aims to characterize a state of the art high-​speed SICM to enable time-​resolved live cell imaging, and do the live cell imaging on human primary keratinocytes to study the related disease. Biomedical Engineering, Electrical and Electronic Engineering, Information, Computing and Communication Sciences, Manufacturing Engineering, Mechanical Engineering, Nanotechnology Master Thesis

Master Thesis: Fraternal Inhibition in Songbird Brother ETH Zurich Institute of Neuroinformatics Our research group aims to enhance the understanding of human language acquisition and development using songbird as model. We are particularly interested in the evolutionary aspects of language, where two developmental tendencies are observed: convergent and divergent evolution. Convergent evolution refers to the simplification of language complexity, similar to how infants gradually acquire human language. Conversely, divergent evolution involves an increase in complexity, akin to teenagers creating and using novel words to establish unique identities. We propose to investigate whether similar effects are observable in animal vocalization learning, specifically in song learning of zebra finches and to explore the effect of social interaction. To facilitate this investigation, our team has developed a "birdpark," a multimodal recording system that provides a naturalistic social environment for observing and recording multiple zebra finches within a dynamic group context. Learning, Memory, Cognition and Language, Linguistic Processes (incl. Speech Production and Comprehension), Sensory Systems, Signal Processing, Zoology ETH Zurich (ETHZ), Master Thesis, Semester Project