dr. ir. Axel Faes

Postdoctoral Researcher · University of TwenteResearch Affiliate · UHasselt
Self-Explaining AIFederated LearningPrecision Medicine

I build the self-explaining hospital - interpretable, privacy-preserving clinical AI.

Currently
UTwenteMulti-modal AI for early liver-cancer (HCC) detection - AI-HCC (ZonMw)
UHasseltInterpretable block-term tensor models for atrial-fibrillation prediction from 12-lead ECG - FAIR
TheoryBlock-term tensor operator theory & dimension-free privacy for federated learning
Research themesResearch statement →
= +

01 Interpretable, self-explaining models

Block-term and multiway tensor models whose decomposition is the explanation - structure a clinician already reasons about, read straight off the model rather than approximated afterward. The methodological core under everything else.

block-term · multiway tensor

02 Federated learning

Training shared models across institutions without raw data ever leaving them - including the hard case of different modalities and incomplete records, with privacy built in by design.

privacy-preserving · vertical & horizontal FL

03 Self-supervised, multi-modal learning

Backbones that learn from unlabelled, longitudinal data and fuse imaging, omics and clinical signals into a single shared representation for downstream clinical prediction.

self-supervised · multi-modal fusion

04 Neural decoding & tensor regression

Recovering interpretable spatiotemporal structure from high-density brain signals (ECoG / EEG) with tensor regression - where the methodology was forged before it moved to the clinic.

tensor regression · ECoG / EEG
Get in touch

I am open to collaboration on interpretable and federated clinical AI, and to supervising motivated students. The fastest way to reach me is email.

axel.faes@utwente.nl