Neuropsychology and Explainability of AI: A Distributional Approach to the Relationship Between Activation Similarity of Neural Categories in Synthetic Cognition

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pichat, Michael, Campoli, Enola, Pogrund, William, Wilson, Jourdan, Veillet-Guillem, Michael, Melkozerov, Anton, Pichat, Paloma, Gasparian, Armanush, Demarchi, Samuel, Poumay, Judicael
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912115489505280
author Pichat, Michael
Campoli, Enola
Pogrund, William
Wilson, Jourdan
Veillet-Guillem, Michael
Melkozerov, Anton
Pichat, Paloma
Gasparian, Armanush
Demarchi, Samuel
Poumay, Judicael
author_facet Pichat, Michael
Campoli, Enola
Pogrund, William
Wilson, Jourdan
Veillet-Guillem, Michael
Melkozerov, Anton
Pichat, Paloma
Gasparian, Armanush
Demarchi, Samuel
Poumay, Judicael
contents We propose a neuropsychological approach to the explainability of artificial neural networks, which involves using concepts from human cognitive psychology as relevant heuristic references for developing synthetic explanatory frameworks that align with human modes of thought. The analogical concepts mobilized here, which are intended to create such an epistemological bridge, are those of categorization and similarity, as these notions are particularly suited to the categorical "nature" of the reconstructive information processing performed by artificial neural networks. Our study aims to reveal a unique process of synthetic cognition, that of the categorical convergence of highly activated tokens. We attempt to explain this process with the idea that the categorical segment created by a neuron is actually the result of a superposition of categorical sub-dimensions within its input vector space.
format Preprint
id arxiv_https___arxiv_org_abs_2411_07243
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Neuropsychology and Explainability of AI: A Distributional Approach to the Relationship Between Activation Similarity of Neural Categories in Synthetic Cognition
Pichat, Michael
Campoli, Enola
Pogrund, William
Wilson, Jourdan
Veillet-Guillem, Michael
Melkozerov, Anton
Pichat, Paloma
Gasparian, Armanush
Demarchi, Samuel
Poumay, Judicael
Neurons and Cognition
Artificial Intelligence
Neural and Evolutionary Computing
We propose a neuropsychological approach to the explainability of artificial neural networks, which involves using concepts from human cognitive psychology as relevant heuristic references for developing synthetic explanatory frameworks that align with human modes of thought. The analogical concepts mobilized here, which are intended to create such an epistemological bridge, are those of categorization and similarity, as these notions are particularly suited to the categorical "nature" of the reconstructive information processing performed by artificial neural networks. Our study aims to reveal a unique process of synthetic cognition, that of the categorical convergence of highly activated tokens. We attempt to explain this process with the idea that the categorical segment created by a neuron is actually the result of a superposition of categorical sub-dimensions within its input vector space.
title Neuropsychology and Explainability of AI: A Distributional Approach to the Relationship Between Activation Similarity of Neural Categories in Synthetic Cognition
topic Neurons and Cognition
Artificial Intelligence
Neural and Evolutionary Computing
url https://arxiv.org/abs/2411.07243