PhD student at University of Geneva and Hes-so Valais (since 2018)

I am a PhD student with double affiliation at the computer science faculty at the University of Geneva and at the University of Applied Sciences of Western Switzerland (Hes-so Valais). My research aims at improving the interpretability of machine learning systems for healthcare. I was a visiting student at the Martinos Center, part of Harvard Medical School in Boston, MA, USA to focus on the interaction between clinicians and deep learning systems. Coming from a background of IT Engineering, I was awarded the Engineering Department Award for completing the MPhil in Machine Learning, Speech and Language Technology at the University of Cambridge (UK) in 2017. 

Current projects

Human-centric interpretability for histopathologyExplanations of machine learning models should facilitate the deployment of automated systems in the pathology workflow. To do so, explaining black-box models should take into account the requirements and domain ontology of the end-users.
User-based evaluation of explainability methodsHuman-centric approaches to explain machine learning decisions consider the user’s need in the XAI development. End-users should be introduced in the evaluation loop to quantify the increase of confidence in the machine learning method, the impact on the final decisions.
Interpretability for the media industryWith the AI4Media project, we collaborate to make sure that the European values of ethical and trustworthy AI are embedded in future AI deployments.
Epistemic uncertainty weighting of user-controlled losses to guide CNN trainingOur recent work on guiding CNN training by user-friendly concepts, e.g. clinical concepts for histopathology, had a main limitation in the formulation of the loss. We address this by epistemic uncertainty weighting.


MPhil in Machine Learning and Machine Intelligence
(2016 – 2017) University of Cambridge (UK); Engineering Department Award;
Master Thesis: Improved Interpretability and Generalisation for Deep Learning

During my thesis project, I worked on a spatial smoothing loss function that would allow for target-specific regularization for recurrent natural language models.

MSc in Artifcial Intelligence and Robotics
(2015-2016 Interrupted) University of Rome La Sapienza (IT); interrupted at 24/120 credits; A+ grades in Probabilistic Methods for Experimental Data Analysis; AI and Machine Learning; Neural Networks.

I interrupted this MSc to apply to the MPhil in Cambridge, as it was more suited to my academic interests.

BEng. in IT
(2013 – 2015) University of Rome La Sapienza (IT); Laziodisu grant for meritorious students; BCC Award;

Dissertation: Studying the control of non invasive prosthetic hands over large time spans

Skills in brief I speak Italian, English and French. I understand Spanish and can interact at a basic level. I mostly program in Python, Tensorflow and Keras. I have experience with Matlab and C programming.

%d blogger hanno fatto clic su Mi Piace per questo: