Marco Bonizzato

Associate Academic Member

Assistant Professor, Polytechnique Montréal, Department of Electrical Engineering

Adjunct Professor, Université de Montréal, Department of Neurosciences

Research Topics

Blackbox Optimization

Computational Neuroscience

Dynamical Systems

Google Scholar

Biography

Marco Bonizzato is a control, electrical and life sciences engineer with over ten years’ experience in implantable brain-computer interfaces and neuromodulation technology. He has unique double expertise in (a) neural prostheses, and (b) machine intelligence and optimization.

Bonizzato is an assistant professor of electrical engineering at Polytechnique Montréal and an adjunct professor of neuroscience at Université de Montréal.

He also directs the Polytechnique’s sciNeurotech Lab, whose research goal is to develop the entire translational arc of new neurostimulation therapies aimed at restoring sensorimotor function after neurotrauma—from discovery in rodents to application in human medical technologies tailored and personalized to the user using AI.

Current Students

Alireza Aminian

PhD - Polytechnique Montréal

Davide Burchielli

PhD - Polytechnique Montréal

Google Scholar

Juan Guerra

Master's Research - Polytechnique Montréal

Co-supervisor :

PhD - Université de Montréal

Github

Nicolas Nicolas

Master's Research - Polytechnique Montréal

Github

Mauricio Rivera

Master's Research - Université de Montréal

mauriv2010@gmail.com

Salamanca-Giron Salamanca-Giron

Postdoctorate - Polytechnique Montréal

Website

Github

Publications

Robust prior-biased acquisition function for human-in-the-loop Bayesian optimization

Rose Guay-Hottin

Lison Kardassevitch

Hugo Pham

Guillaume Lajoie

Marco Bonizzato

2025-01-01

Knowl. Based Syst. (published)

doi.org

Modulation of leg trajectory by transcranial magnetic stimulation during walking

H. Bourgeois

Rose Guay-Hottin

E.-M. Meftah

M. Martinez

Marco Bonizzato

D. Barthélemy

2024-10-23

bioRxiv (preprint)

doi.org

Modulation of leg trajectory by transcranial magnetic stimulation during walking

H. Bourgeois

Rose Guay-Hottin

E.-M. Meftah

M. Martinez

Marco Bonizzato

D. Barthélemy

The primary motor cortex is involved in initiation and adaptive control of locomotion. However, the role of the motor cortex in controlling … (see more)gait trajectories remains unclear. In animals, cortical neuromodulation allows for precise control of step height. We hypothesized that a similar control framework applies to humans, whereby cortical stimulation would primarily increase foot elevation. Transcranial magnetic stimulation (TMS) was applied over the motor cortex to assess the involvement of the corticospinal tract over the limb trajectory during human walking. Eight healthy adults (aged 20-32 years) participated in treadmill walking at 1.5 km/h. TMS was applied over the left motor cortex at an intensity of 120% of the threshold to elicit a dorsiflexion of the right ankle during the swing phase of gait. Electromyographic (EMG) measurements and three-dimensional (3D) lower limb kinematics were collected. When delivered during the early swing phase, TMS led to a significant increase in the maximum height of the right toe by a mean of 40.7% ± 14.9% (25.6mm ± 9.4 mm, p = 0.0352) and knee height by 57.8%± 16.8%; (32mm ± 9.3 mm; p = 0.008) across participants. These findings indicate that TMS can influence limb trajectory during walking, highlighting its potential as a tool for studying cortical control of locomotion.

2024-10-23

bioRxiv (preprint)

doi.org

Hallucination Detox: Sensitive Neuron Dropout (SeND) for Large Language Model Training

Shahrad Mohammadzadeh

Juan David Guerra

Marco Bonizzato

Reihaneh Rabbany

Golnoosh Farnadi

As large language models (LLMs) are increasingly deployed across various industries, concerns regarding their reliability, particularly due … (see more)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 Sensitivity Dropout (SenD), a novel training protocol designed to mitigate hallucinations by reducing variance during training. SenD achieves this by deterministically dropping embedding indices with significant variability, referred to as Sensitive Embedding Indices. In addition, we develop an unsupervised hallucination detection metric, Efficient EigenScore (EES), which approximates the traditional EigenScore at 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 Wikipedia, Medical, and LegalBench domains.

2024-10-20

ArXiv (preprint)

doi.org

arxiv.org

Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training

Shahrad Mohammadzadeh

Juan David Guerra

Marco Bonizzato

Reihaneh Rabbany

Golnoosh Farnadi

2024-10-20

ArXiv (preprint)

arxiv.org

Hallucination Detox: Sensitive Neuron Dropout (SeND) for Large Language Model Training

Shahrad Mohammadzadeh

Juan David Guerra

Marco Bonizzato

Reihaneh Rabbany

Golnoosh Farnadi

As large language models (LLMs) become increasingly deployed across various industries, concerns regarding their reliability, particularly d… (see more)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.

2024-10-12

NeurIPS.cc/2024/Workshop/SafeGenAi (poster)

doi.org

openreview.net

Gaussian-process-based Bayesian optimization for neurostimulation interventions in rats

Léo Choinière

Rose Guay-Hottin

Rémi Picard

Guillaume Lajoie

Marco Bonizzato

Numa Dancause

2024-02-14