français
Home > About us > News > Team Barbier News
See the complete sitemapGraphs for Artificial Neural Networks and Brain Connectivity Exploration
on the October 20, 2023
2 p.m.
2 p.m.
PhD defense of Lucrezia Carboni
On Friday October 20th 2023, Lucrezia CARBONI will defend her thesis "Graphs for Artificial Neural Networks and Brain Connectivity Exploration".
This thesis has been directed by Sophie ACHARD of the Statify-LJK team and Michel DOJAT of the "Functional Neuroimaging and Brain Perfusion" team of the GIN.
Thesis committee :
- Bertrand THIRION, Directeur de Recherche, Inria Saclay - Reviewer
- Nicolas FARRUGIA, Maître de conférence, IMT Atlantique - Reviewer
- Nadia BRAUNER, Professeure des Universités, Université Grenoble Alpes - Examiner
- Ana MARQUES, Practicienne Hospitalière HDR, CHU Clermont-Ferrand - Examiner
- Giulia PRETI, Docteure en Sciences, Researcher at CENTAI Research Institute Turin - Examiner
- Sophie ACHARD, Directrice de Recherche, CNRS, Statify-LJK Université Grenoble Alpes - Supervisor
- Michel DOJAT, Directeur de Recherche, INSERM, Grenoble Institut des Neurosciences - Supervisor
- Marina Reyboz, Ingénieure de Recherche HDR, CEA Grenoble - Guest
- Paulo Gonçalves, Directeur de Recherche, Inria Rhône-Alpes et ENS Lyon - Guest
Abstract :
The main objective of this thesis is to explore brain and artificial neural network connectivity from a graph-based perspective. While structural and functional connectivity analysis has been extensively studied in the context of the human brain, there is a lack of a similar analysis framework in artificial systems. To address this gap, this research focuses on two main axes.In the first axis, the main objective is to determine a healthy signature characterization of the human brain resting state functional connectivity. A novel framework is proposed to achieve this objective, integrating traditional graph statistics and network reduction tools to determine healthy connectivity patterns. Hence, we build a graph pair-wise comparison and a classifier to identify pathological states and rank associated perturbed brain regions. Additionally, the generalization and robustness of the proposed framework were investigated across multiple datasets and variations in data quality.
The second research axis explores the benefits of brain-inspired connectivity exploration of artificial neural networks (ANNs) in the future perspective of more robust artificial systems development. A major robustness issue in ANN models is represented by catastrophic forgetting when the network dramatically forgets previously learned tasks when adapting to new ones. Our work demonstrates that graph modeling offers a simple and elegant framework for investigating ANNs, comparing different learning strategies, and detecting deleterious behaviors such as catastrophic forgetting.
Moreover, we explore the potential of leveraging graph-based insights to mitigate effectively catastrophic forgetting, laying a foundation for future research and explorations in this area.
