Search Results for author: Victor Boutin

Found 7 papers, 4 papers with code

An adaptive homeostatic algorithm for the unsupervised learning of visual features

1 code implementation ICLR 2019 Victor Boutin, Angelo Franciosini, Laurent Perrinet

The formation of structure in the brain, that is, of the connections between cells within neural populations, is by large an unsupervised learning process: the emergence of this architecture is mostly self-organized.

Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?

no code implementations27 Jan 2023 Victor Boutin, Thomas Fel, Lakshya Singhal, Rishav Mukherji, Akash Nagaraj, Julien Colin, Thomas Serre

An important milestone for AI is the development of algorithms that can produce drawings that are indistinguishable from those of humans.

Diversity vs. Recognizability: Human-like generalization in one-shot generative models

1 code implementation20 May 2022 Victor Boutin, Lakshya Singhal, Xavier Thomas, Thomas Serre

Robust generalization to new concepts has long remained a distinctive feature of human intelligence.


Effect of top-down connections in Hierarchical Sparse Coding

1 code implementation3 Feb 2020 Victor Boutin, Angelo Franciosini, Franck Ruffier, Laurent Perrinet

In this study, a new model called 2-Layers Sparse Predictive Coding (2L-SPC) is introduced to assess the impact of this inter-layer feedback connection.

Sparse Deep Predictive Coding captures contour integration capabilities of the early visual system

1 code implementation20 Feb 2019 Victor Boutin, Angelo Franciosini, Frederic Chavane, Franck Ruffier, Laurent Perrinet

Third, we demonstrate at the representational level that the SDPC feedback connections are able to overcome noise in input images.

Association Decision Making

From biological vision to unsupervised hierarchical sparse coding

no code implementations4 Dec 2018 Victor Boutin, Angelo Franciosini, Franck Ruffier, Laurent U. Perrinet

The formation of connections between neural cells is emerging essentially from an unsupervised learning process.

Cannot find the paper you are looking for? You can Submit a new open access paper.