Beyond Human Perception: Challenges in AI Interpretability of Orangutan Artwork - Systèmes d’Informations Généralisées
Pré-Publication, Document De Travail Année : 2024

Beyond Human Perception: Challenges in AI Interpretability of Orangutan Artwork

Résumé

Drawings serve as a profound medium of expression for both humans and apes, offering unique insights into the cognitive and emotional landscapes of the artists, regardless of their species. This study employs artificial intelligence (AI), specifically Convolutional Neural Networks (CNNs) and the interpretability tool Captum, to analyze non-figurative drawings by Molly, an orangutan. The research utilizes VGG19 and ResNet18 models to

Click here to view linked References decode seasonal nuances in the drawings, achieving notable accuracy in seasonal classification and revealing complex influences beyond human-centric methods. Techniques such as occlusion, integrated gradients, PCA, t-SNE, and Louvain clustering highlight critical areas and elements influencing seasonal recognition, providing deeper insights into the drawings. This approach not only advances the analysis of non-human art but also demonstrates the potential of AI to enrich our understanding of non-human cognitive and emotional expressions, with significant implications for fields like evolutionary anthropology and comparative psychology.

Fichier principal
Vignette du fichier
PRIM-2024.pdf (715.89 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04714755 , version 1 (30-09-2024)

Identifiants

  • HAL Id : hal-04714755 , version 1

Citer

Cedric Sueur, Elliot Maître, Jimmy Falck, Masaki Shimada, Marie Pelé. Beyond Human Perception: Challenges in AI Interpretability of Orangutan Artwork. 2024. ⟨hal-04714755⟩
0 Consultations
0 Téléchargements

Partager

More