1.4k citations
- Centre National de la Recherche ScientifiqueFR37 papers
- Université Fédérale de Toulouse Midi-PyrénéesFR17 papers
- Université Toulouse III - Paul SabatierFR16 papers
- Université de ToulouseFR13 papers
- University of TehranIR8 papers
- Institut de Recherche en Informatique de ToulouseFR7 papers
- Brown UniversityUS5 papers
- InsermFR4 papers
- Institut de la VisionFR4 papers
- Allen Institute for Brain ScienceUS3 papers
- Image and Pervasive Access LaboratorySG3 papers
- Institute for Infocomm ResearchSG3 papers
55 papers
Binary Spiking Neural Networks as Causal Models
Aditya Kar, Emiliano Lorini, Timothée Masquelier
We provide a causal analysis of Binary Spiking Neural Networks (BSNNs) to explain their behavior. We formally define a BSNN and represent its spiking activity as a binary causal mo…
An Attention Mechanism for Robust Multimodal Integration in a Global Workspace Architecture
Roland Bertin-Johannet, Lara Scipio, Leopold Maytié +1
Robust multimodal systems must remain effective when some modalities are noisy, degraded, or unreliable. Existing multimodal fusion methods often learn modality selection jointly w…
AI Consciousness and Existential Risk
Rufin VanRullen
In AI, the existential risk denotes the hypothetical threat posed by an artificial system that would possess both the capability and the objective, either directly or indirectly, t…
GASPnet: Global Agreement to Synchronize Phases
Andrea Alamia, Sabine Muzellec, Thomas Serre +1
In recent years, Transformer architectures have revolutionized most fields of artificial intelligence, relying on an attentional mechanism based on the agreement between keys and q…
Dreaming up scale invariance via inverse renormalization group
Adam Rançon, Ulysse Rançon, Tomislav Ivek +1
We explore how minimal neural networks can invert the renormalization group (RG) coarse-graining procedure in the two-dimensional Ising model, effectively ``dreaming up'' microscop…
Wave propagation phenomena in nonlinear hierarchical neural networks with predictive coding feedback dynamics
Andrea Alamia, Léa Dalliès, Grégory Faye +1
We propose a mathematical framework to systematically explore the propagation properties of a class of continuous in time nonlinear neural network models comprising a hierarchy of…