Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Category learning in deep neural networks: Information content and geometry of internal representations
Laurent Bonnasse-Gahot, Jean-Pierre Nadal
In humans and other animals, category learning enhances discrimination between stimuli close to the category boundary. This phenomenon, called categorical perception, was also empi…
cs.LG2023
Information theoretic study of the neural geometry induced by category learning
Laurent Bonnasse-Gahot, Jean-Pierre Nadal
Categorization is an important topic both for biological and artificial neural networks. Here, we take an information theoretic approach to assess the efficiency of the representat…