Hi! I am a post-doc researcher in AI interpretability for bio-medical research and discovery. I sit on the bridge between biomedicine and technology, with the aim of discovering how AI can enrich our understanding of pathologies.
I hold a Ph.D. in Computer Science from the University of Geneva and my Ph.D. dissertation received the best thesis award from the IEEE Technical Committee on Computational Life Sciences. I also hold a MPhil in Machine Learning, Speech and Language from the University of Cambridge.
This website hosts a collection and summary of my work, talks and hints on the small habits that keep me living a happy and satisfying life.
Latest Talks
I’m mentoring Task 1 on the MICCAI Hackathon 2022, with a brand new challenge on how to assess data shift due to multiple annotators with different biases! Check this up here.
“Interpretability of DL for microscopy imaging: Importance, Utility, Impact“. Invited Lecture at the Pathology congress on “Quality Improvement in Clinical Laboratories”, in the session on Artificial Intelligence, Data Science and Laboratory Medicine. Here the slides.
“DL Interpretability for the discovery of biomedical patterns” at the Interpretability in AI Workshop at Banff International Research Station (BIRS) for Mathematical Innovation and Discovery
Publications
Attention-based Interpretable Regression of Gene Expression in Histology, iMIMIC at MICCAI 2022
A Global Taxonomy of Interpretable AI: Unifying the Terminology for the Technical and the Social Sciences, Artificial Intelligence Review
Learning Interpretable Diagnostic Features of Tumor by Multi-task Adversarial Training of Convolutional Networks: Improved Generalization, preprint under review
On the Scale Invariance in State of the Art CNNs Trained on Imagenet, Machine Learning and Knowledge Extraction
Mentoring: Work with intention and joy
I share here a collection of posts and interesting readings on how to reach a healthy balance between work and private life.
Better saying nothing than anything useless.
The aim of this website is to provide information that is useful.
Feel free to leave feedback. Discussions are welcome. Drop me an email with what you think!
Qualifications
Ph. D. in Computer Science (Univ. Geneva), Deep Learning Interpretability for Medical Imaging * Best thesis award (IEEE TCCLS)
MPhil in Machine Learning and Machine Intelligence (Univ. Cambridge), Improved Interpretability and Generalisation in Deep Learning * Eng. Department Award
BEng. IT Engineering (Univ. Roma La Sapienza), Repeatability of Machine Learning Predictions for Surface Electromyography Signals * Excellent Thesis Award by Laziodisu
Mara Graziani 