Ajout du séminaire CONECT par Victor Boutin avec détails sur l'événement et l'intervenant

Author: laurentperrinet

content/event/2025-02-27_seminaire-Victor-Boutin/featured.jpg

@@ -0,0 +1,30 @@
+---
+authors:
+- laurent-u-perrinet
+date: 2025-02-27
+publishDate: 2025-01-27
+draft: false
+image:
+  focal_point: Center
+  placement: 2
+  preview_only: true
+projects: []
+tags:
+- events
+title: '2025-02-27 : CONECT seminar by Victor Boutin'
+subtitle: '"FReverse Engineering Human Generalization using Artificial Intelligence."'
+summary: 'CONECT seminar by Victor Boutin: "Reverse Engineering Human Generalization using Artificial Intelligence".'
+---
+
+
+* When: February 27th ***14:00 to 16:00*** 
+* Where: _Institut de Neurosciences de la Timone_, Marseille, France.
+
+During this CONECT seminar, [Dr Victor Boutin](https://victorboutin.github.io/) will present his recent work in machine learning: **Reverse Engineering Human Generalization using Artificial Intelligence**.
+
+> Abstract: Although nearly every pair of objects we encounter is unique, we can consistently infer their properties based on knowledge acquired from previous experiences. This ability to transfer knowledge to new situations is called generalization and is pervasive in cognitive science. How do we generalize? In this presentation, I summarize my current results, and outline future perspectives, offering valuable insight to address this question. Cognitive scientists suggest a generalization circuit in the brain that i) extracts a disentangled and versatile representation of the sensory stimuli and ii) learns a powerful generative model of its environment. In my work, I use state-of-the-art deep learning algorithms to model those two aspects of brain computation. These models are validated through human/machine comparison on tasks inspired by cognitive science. As a case in point, I recently compared the generalization abilities of modern generative AI systems against those of humans on the one-shot drawing tasks. I demonstrate that the gap between humans and machines has started to close since the introduction of diffusion models, but that qualitative differences remain. Those differences are explainable by discrepancies in visual strategies between humans and current AI systems. The unique scientific method of my work not only allows me to uncover the computational mechanisms underpinning human generalization but also provides me with a principled path to create AI systems that are better aligned with human behavior.
+
+
+{{% callout note %}}
+Victor Boutin is a researcher at CNRS, based at the Brain and Cognition Research Center (CerCo), in Toulouse, within the NeuroAI team. He received a Ph.D in Computational Neuroscience and Artificial Intelligence from Aix-Marseille University in 2020, and was graduated from Ecole Centrale Marseille in 2011 where he majored in Statistics and Applied Mathematics. From 2020 to 2022, he served as a Postdoctoral Research Associate at the Artificial and Natural Intelligence Toulouse Institute (ANITI), and from 2022 to 2024, he was a senior Postdoctoral researcher at Brown University's SerreLab in Providence, US. Victor’s research leverages cutting-edge AI algorithms to explore the computational mechanisms in the brain that enable its exceptional generalization capabilities. 
+{{% /callout %}}