Oscillations in an artificial neural network convert competing inputs into a temporal code
PLOS Computational Biology · 2024
DOI: 10.1371/journal.pcbi.1012429 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, 2024. Verfasst von Katharina Duecker und 3 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Human Brain Health, School of Psychology, University of Birmingham, Birmingham, United Kingdom. Hauptthemen laut MEDLINE: Neural Networks, Computer, Models, Neurological, Computational Biology. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 132 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wellcome Trust, National Institute for Health and Care Research Applied Research Collaboration Oxford and Thames Valley, Brazilian Government.
Abstract (Originalsprache)
The field of computer vision has long drawn inspiration from neuroscientific studies of the human and non-human primate visual system. The development of convolutional neural networks (CNNs), for example, was informed by the properties of simple and complex cells in early visual cortex. However, the computational relevance of oscillatory dynamics experimentally observed in the visual system are typically not considered in artificial neural networks (ANNs). Computational models of neocortical dynamics, on the other hand, rarely take inspiration from computer vision. Here, we combine methods from computational neuroscience and machine learning to implement multiplexing in a simple ANN using oscillatory dynamics. We first trained the network to classify individually presented letters. Post-training, we added temporal dynamics to the hidden layer, introducing refraction in the hidden units as well as pulsed inhibition mimicking neuronal alpha oscillations. Without these dynamics, the trained network correctly classified individual letters but produced a mixed output when presented with two letters simultaneously, indicating a bottleneck problem. When introducing refraction and oscillatory inhibition, the output nodes corresponding to the two stimuli activate sequentially, ordered along the phase of the inhibitory oscillations. Our model implements the idea that inhibitory oscillations segregate competing inputs in time. The results of our simulations pave the way for applications in deeper network architectures and more complicated machine learning problems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Centre for Human Brain Health, School of Psychology, University of Birmingham, Birmingham, United Kingdom.
- Department of Neuroscience, Brown University, Providence, Rhode Island, United States of America.
- Institute of Physics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil.
- Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, the Netherlands.
ORCID-Profile: Katharina Duecker
Förderung
- Wellcome Trust
- National Institute for Health and Care Research Applied Research Collaboration Oxford and Thames Valley
- Brazilian Government
- Dutch Ministry of Education (OCW) via the Dutch Research Council
- Wellcome Trust Discovery Award
- NIHR Oxford Health Biomedical Research Centre
Zitieren
APA
Duecker, K., Idiart, M., van Gerven, M., & Jensen, O. (2024). Oscillations in an artificial neural network convert competing inputs into a temporal code. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1012429
Vancouver
Duecker K, Idiart M, van Gerven M, Jensen O. Oscillations in an artificial neural network convert competing inputs into a temporal code. PLOS Computational Biology. 2024. doi:10.1371/journal.pcbi.1012429
BibTeX
@article{Duecker2024,
author = {Duecker, Katharina and Idiart, Marco and van Gerven, Marcel and Jensen, Ole},
title = {Oscillations in an artificial neural network convert competing inputs into a temporal code},
journal = {PLOS Computational Biology},
year = {2024},
doi = {10.1371/journal.pcbi.1012429}
}
EUVIMED