Frédéric Alexandre
YOU?
Author Swipe
View article: Visual Large Language Models Exhibit Human-Level Cognitive Flexibility in the Wisconsin Card Sorting Test
Visual Large Language Models Exhibit Human-Level Cognitive Flexibility in the Wisconsin Card Sorting Test Open
Cognitive flexibility has been extensively studied in human cognition but remains relatively unexplored in the context of Visual Large Language Models (VLLMs). This study assesses the cognitive flexibility of state-of-the-art VLLMs (GPT-4o…
View article: Décrypter les processus cognitifs dans la résolution créative de problèmes : une approche computationnelle.
Décrypter les processus cognitifs dans la résolution créative de problèmes : une approche computationnelle. Open
We propose a critical review of the research literature regarding creativity, which is required for creative problem-solving during a learning task, aiming to study this process from a triple perspective combining the neurosciences, the le…
View article: Modélisation de tâches créatives de résolution de problèmes à partir d'une approche computationnelle et neuroéducative
Modélisation de tâches créatives de résolution de problèmes à partir d'une approche computationnelle et neuroéducative Open
Creativity is a complex process that has been studied in different fields with a high level of diversity in relation to the types of tasks, contexts, and assessment methodologies. In this study, we focus on ill-defined individual creative …
View article: The systematic nature of splitter cells
The systematic nature of splitter cells Open
During the past decades, hippocampal formation has undergone extensive studies, leading researchers to identify a vast collection of cells with functional properties. Several investigations, supported by carefully crafted models, have exam…
View article: Learning Artificial Intelligence Through Open Educational Resources
Learning Artificial Intelligence Through Open Educational Resources Open
This chapter discusses the creation and impact of a Massive Open Online Course (MOOC) titled ‘Artificial Intelligence with Intelligence (IAI)’ aimed at fostering a culture of AI understanding and participation in ethical debates. The chapt…
View article: Contextual Control of Hopfield Networks in a Hippocampal Model
Contextual Control of Hopfield Networks in a Hippocampal Model Open
Executive functions guide episodic memory to retrieve information essential for adaptive behavior. The prefrontal cortex achieves this by influencing hippocampal processing through anatomical projections targeting the entorhinal cortex and…
View article: Relating Hopfield Networks to Episodic Control
Relating Hopfield Networks to Episodic Control Open
Neural Episodic Control is a powerful reinforcement learning framework that employs a differentiable dictionary to store non-parametric memories. It was inspired by episodic memory on the functional level, but lacks a direct theoretical co…
View article: Modelling Cross-Situational Learning on Full Sentences in Few Shots with Simple RNNs
Modelling Cross-Situational Learning on Full Sentences in Few Shots with Simple RNNs Open
How do children bootstrap language through noisy supervision? Most prior works focused on tracking co-occurrences between individual words and referents. We model cross-situational learning (CSL) at sentence level with few (1000) training …
View article: MEG Encoding using Word Context Semantics in Listening Stories
MEG Encoding using Word Context Semantics in Listening Stories Open
International audience
View article: Deep Neural Networks and Brain Alignment: Brain Encoding and Decoding (Survey)
Deep Neural Networks and Brain Alignment: Brain Encoding and Decoding (Survey) Open
Can artificial intelligence unlock the secrets of the human brain? How do the inner mechanisms of deep learning models relate to our neural circuits? Is it possible to enhance AI by tapping into the power of brain recordings? These captiva…
View article: Long Short-Term Memory of Language Models for Predicting Brain Activation During Listening to Stories
Long Short-Term Memory of Language Models for Predicting Brain Activation During Listening to Stories Open
International audience
View article: From concrete to abstract rules : A computational sketch
From concrete to abstract rules : A computational sketch Open
International audience
View article: Cross-Situational Learning Towards Robot Grounding
Cross-Situational Learning Towards Robot Grounding Open
How do children acquire language through unsupervised or noisy supervision? How do their brain process language? We take this perspective to machine learning and robotics, where part of the problem is understanding how language models can …
View article: From implicit learning to explicit representations
From implicit learning to explicit representations Open
Using the reservoir computing framework, we demonstrate how a simple model can solve an alternation task without an explicit working memory. To do so, a simple bot equipped with sensors navigates inside a 8-shaped maze and turns alternativ…
View article: Ontology as manifold: towards symbolic and numerical artificial embedding
Ontology as manifold: towards symbolic and numerical artificial embedding Open
International audience
View article: Developmental Modular Reinforcement Learning
Developmental Modular Reinforcement Learning Open
In this article, we propose a modular reinforcement learning (MRL) architecture that coordinates the competition and the cooperation between modules, and inspires, in a developmental approach, the generation of new modules in cases where n…
View article: Ontology as neuronal-space manifold: Towards symbolic and numerical artificial embedding
Ontology as neuronal-space manifold: Towards symbolic and numerical artificial embedding Open
International audience
View article: Towards a Computational Cognitive Neuroscience Model of Creativity
Towards a Computational Cognitive Neuroscience Model of Creativity Open
International audience
View article: Knowledge extraction from the learning of sequences in a long short term memory (LSTM) architecture
Knowledge extraction from the learning of sequences in a long short term memory (LSTM) architecture Open
International audience