Research topics

Research

Machine learning methods for marine data, sensor systems, medical imaging, tabular data, and human activity recognition.

marine data / uncertainty / sensor placement

Neural Processes for Optimal Sensor Placement

Machine learning models for optimal ocean measurement locations using uncertainty-aware Neural Processes.

medical imaging

AI-driven real-time 3D ultrasound analysis for diagnostic and therapy guidance.

large language models / tool use / agents

Methods that let language models call external tools reliably, from function calling and MCP to agents that act on real software systems.

tabular machine learning / categorical data

Deep neural network models for tabular and categorical data beyond tree-based baselines.

human activity recognition / domain adaptation

Domain adaptation methods for human activity recognition across different sensor datasets.

microbiome / machine learning / ecological data

Machine learning methods for high-dimensional microbiome and metabarcoding data.

neuro-symbolic AI / human activity recognition

Neuro-symbolic models for activity recognition that use domain knowledge and constraints.

probabilistic inference / tractable models

Probabilistic models with guarantees on efficient inference operations.

probabilistic inference / dynamic systems

Efficient inference in dynamic probabilistic systems by exploiting symmetries.

explainable AI / neural networks

Methods for understanding which inputs shape neural network decisions.

health data / human activity recognition

Machine learning for detecting disorientation in people with dementia.