Portrait de Marco Bonizzato

Marco Bonizzato

Membre académique associé
Professeur adjoint, Polytechnique Montréal, Département de génie électrique
Professeur adjoint, Université de Montréal, Département de neurosciences
Sujets de recherche
Neurosciences computationnelles
Optimisation en boîte noire
Systèmes dynamiques

Biographie

Marco Bonizzato est ingénieur en contrôle, en électricité et en sciences de la vie, et cumule plus de 10 ans d'expérience dans le domaine des interfaces cerveau-ordinateur implantables et de la technologie de neuromodulation. Il possède une double expertise unique en prothèses neurales et en intelligence et optimisation des machines.

Il est professeur adjoint de génie électrique à Polytechnique Montréal et professeur auxiliaire de neurosciences à l'Université de Montréal.

Il dirige également le laboratoire sciNeurotech. L'objectif de la recherche qui y est menée est de développer l'arc translationnel complet de nouvelles thérapies de neurostimulation afin de restaurer la fonction sensorimotrice après un neurotraumatisme, depuis la découverte chez le rongeur jusqu'à l'application dans la technologie médicale humaine, adaptée et personnalisée à chaque utilisateur par l'intelligence artificielle.

Étudiants actuels

Doctorat - Polytechnique
Maîtrise recherche - Polytechnique
Co-superviseur⋅e :
Maîtrise recherche - Polytechnique
Co-superviseur⋅e :
Doctorat - UdeM
Maîtrise recherche - Polytechnique
Maîtrise recherche - UdeM
Postdoctorat - Polytechnique

Publications

Hallucination Detox: Sensitive Neuron Dropout (SeND) for Large Language Model Training
Shahrad Mohammadzadeh
Juan David Guerra
As large language models (LLMs) become increasingly deployed across various industries, concerns regarding their reliability, particularly d… (voir plus)ue to hallucinations-outputs that are factually inaccurate or irrelevant to user input-have grown. Our research investigates the relationship between the training process and the emergence of hallucinations to address a key gap in existing research that focuses primarily on post hoc detection and mitigation strategies. Using models from the Pythia suite (70M-12B parameters) and several hallucination detection metrics, we analyze hallucination trends throughout training and explore LLM internal dynamics. We introduce SEnsitive Neuron Dropout (SeND), a novel training protocol designed to mitigate hallucinations by reducing variance during training. SeND achieves this by deterministically dropping neurons with significant variability on a dataset, referred to as Sensitive Neurons. In addition, we develop an unsupervised hallucination detection metric, Efficient EigenScore (EES), which approximates the traditional EigenScore in 2x speed. This efficient metric is integrated into our protocol, allowing SeND to be both computationally scalable and effective at reducing hallucinations. Our empirical evaluation demonstrates that our approach improves LLM reliability at test time by up to 40% compared to normal training while also providing an efficient method to improve factual accuracy when adapting LLMs to domains such as Wikipedia and Medical datasets.
Gaussian-process-based Bayesian optimization for neurostimulation interventions in rats
Léo Choinière
Rose Guay-Hottin
Rémi Picard
Numa Dancause
Invasive Brain Computer Interface for Motor Restoration in Spinal Cord Injury: A Systematic Review.
Jordan J. Levett
Lior M. Elkaim
Farbod Niazi
Michael H. Weber
Christian Iorio-Morin
Alexander G. Weil
Autonomous optimization of neuroprosthetic stimulation parameters that drive the motor cortex and spinal cord outputs in rats and monkeys
Rose Guay Hottin
Sandrine L. Côté
Elena Massai
Léo Choinière
Uzay Macar
Samuel Laferrière
Parikshat Sirpal
Stephan Quessy
Marina Martinez
Numa Dancause
Use of Invasive Brain-Computer Interfaces in Pediatric Neurosurgery: Technical and Ethical Considerations
David Bergeron
Christian Iorio-Morin
Nathalie Orr Gaucher
Éric Racine
Alexander G. Weil
Implementing automation in deep brain stimulation: has the time come?
Alfonso Fasano