EUVIMEDEUVIMED entdecken
Crossref

Associative Emotional Learning in Convolutional Neural Networks

Seowung Leem, Andreas Keil, Mingzhou Ding, Ruogu Fang

Neural Computation · 10.11.2026 · 38 (12) · 2280-2307

DOI: 10.1162/neco.a.1580 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neural Computation, online erschienen am 10.11.2026. Verfasst von Seowung Leem und 3 weiteren Autor:innen. Beteiligte Einrichtung: J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL 32611, U.S.A. leem.s@ufl.edu. Hauptthemen laut MEDLINE: Association Learning, Emotions, Neural Networks, Computer. Die Arbeit nennt 91 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Associative emotional learning enables organisms to adaptively link pleasant or unpleasant outcomes to the presence of predictive stimuli. Whereas computational models such as the Rescorla-Wagner model have shed light on this important function, the limitations of these models are also known, especially when they are applied to neural data. The advent of deep neural networks has opened another avenue for modeling associative emotional learning. In this work, we proposed a deep neural network model of visual valence processing, consisting of a visual module that encodes complex natural scenes and a module that recognizes their emotional significance in terms of valence, a key dimension of emotion, and tested a novel Pavlovian learning paradigm on the model. The results showed that with learning, the model reproduced several observations from human associative learning studies, including association formation and generalization, and that the neural representations of the conditioned and the unconditioned stimuli became increasingly aligned at both the single unit and the neural population level. Comparison between the model and human experimental data provided further validation of our approach. This study thus suggests that deep neural network models, when combined with appropriate learning algorithms, can be used to model behavioral and neural signatures of associative emotion/valence learning.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Association LearningEmotionsNeural Networks, ComputerHumansConvolutional Neural NetworksConditioning, ClassicalDeep LearningSoft ComputingModels, NeurologicalAlgorithms

Autor:innen und Institutionen

  • J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL 32611, U.S.A. leem.s@ufl.edu.
  • Center for the Study of Emotion and Attention, University of Florida, Gainesville, FL 32611, U.S.A. akeil@ufl.edu.
  • J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL 32611, U.S.A. MDing@bme.ufl.edu.
  • J. Crayton Pruitt Family Department of Biomedical Engineering; Department of Electrical and Computer Engineering; Department of Computer and Information Science and Engineering; Department of Radiology; and Center for C…

Zitieren

APA

Leem, S., Keil, A., Ding, M., & Fang, R. (2026). Associative Emotional Learning in Convolutional Neural Networks. Neural Computation, 38(12), 2280-2307. https://doi.org/10.1162/neco.a.1580

Vancouver

Leem S, Keil A, Ding M, Fang R. Associative Emotional Learning in Convolutional Neural Networks. Neural Computation. 2026;38(12):2280-2307. doi:10.1162/neco.a.1580

BibTeX
@article{Leem2026,
  author = {Leem, Seowung and Keil, Andreas and Ding, Mingzhou and Fang, Ruogu},
  title = {Associative Emotional Learning in Convolutional Neural Networks},
  journal = {Neural Computation},
  year = {2026},
  volume = {38},
  number = {12},
  pages = {2280--2307},
  doi = {10.1162/neco.a.1580}
}
Kostenlos starten →