EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Biologically inspired deep neural network models for visual emotion processing

Peng Liu, Ke Bo, Yujun Chen, Andreas Keil, Mingzhou Ding, Ruogu Fang

Network Neuroscience · 30.10.2026 · 10 (4) · 1072-1098

DOI: 10.1162/netn.a.596 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Network Neuroscience, online erschienen am 30.10.2026. Verfasst von Peng Liu und 5 weiteren Autor:innen. Die Arbeit nennt 82 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, National Institutes of Health/National Institute of Mental Health, University of Florida.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The perception of opportunities and threats in complex visual scenes represents one of the main functions of the human visual system. The underlying neurophysiology is often studied by having observers view pictures varying in affective content. While deep neural networks (DNNs) have shown promise in modeling visual recognition of objects, their capacity to model visual affective processing remains to be better understood. In this study, we proposed a biologically inspired deep neural network model, referred to as the visual cortex amygdala (VCA) model, for this purpose. The model integrates a vision transformer module for visual encoding and an amygdala-mimetic module that incorporates an anatomical hierarchy and self-attention-based computational mechanisms for affective decoding. We evaluated the model along three dimensions: (a) predictive accuracy for emotional valence and arousal, (b) representational alignment with human amygdala activity, and (c) internal organization of emotion representation within the model. The results showed that (a) the model can predict with high accuracy human emotion ratings on 1,182 images from the International Affective Picture System (IAPS) dataset (valence: r ≈ 0.9; arousal: r ≈ 0.7), (b) the model’s internal representations aligned with functional magnetic resonance imaging (fMRI) data from the human amygdala, and (c) at the single model neuron level, the amygdala module evolved emotion selectivity; in addition, at the model neural population level, deeper layers of the amygdala module developed representational geometry that is progressively more aligned with affective dimensions. We also explored the effect of visual encoding and the effect of structure and computational mechanisms on emotional assessment.

Förderung

  • National Science Foundation
  • National Institutes of Health/National Institute of Mental Health
  • University of Florida
  • University of Florida Informatics Institute

Zitieren

APA

Liu, P., Bo, K., Chen, Y., Keil, A., Ding, M., & Fang, R. (2026). Biologically inspired deep neural network models for visual emotion processing. Network Neuroscience, 10(4), 1072-1098. https://doi.org/10.1162/netn.a.596

Vancouver

Liu P, Bo K, Chen Y, Keil A, Ding M, Fang R. Biologically inspired deep neural network models for visual emotion processing. Network Neuroscience. 2026;10(4):1072-1098. doi:10.1162/netn.a.596

BibTeX
@article{Liu2026,
  author = {Liu, Peng and Bo, Ke and Chen, Yujun and Keil, Andreas and Ding, Mingzhou and Fang, Ruogu},
  title = {Biologically inspired deep neural network models for visual emotion processing},
  journal = {Network Neuroscience},
  year = {2026},
  volume = {10},
  number = {4},
  pages = {1072--1098},
  doi = {10.1162/netn.a.596}
}
Kostenlos starten →