EUVIMEDEUVIMED entdecken
Übersichtsarbeit

Foundation Models for Neural Signal Decoding: EEG‐Centered Perspectives Toward Unified Representations

Jii Kwon, Youmin Shin iD

European Journal of Neuroscience · 2026-01 · 63 (1)

DOI: 10.1111/ejn.70376 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift European Journal of Neuroscience, online erschienen am 29.12.2025. Verfasst von Jii Kwon und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Brain & Cognitive Sciences, Seoul National University, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Electroencephalography, Brain, Models, Neurological. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 138 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural signals such as EEG, ECoG, and intracortical recordings offer a valuable window into brain dynamics but remain difficult to decode due to high dimensionality, nonstationarity, and substantial interindividual variability. Traditional machine learning and deep learning models often show limited generalizability and insufficient interpretability in these settings. Foundation models (FMs)—large‐scale architectures pretrained on diverse datasets—have recently emerged as a promising paradigm for building robust, transferable, and physiologically grounded neural representations. Among these modalities, EEG currently serves as the most practical and representative platform for FM development due to its large‐scale open datasets, standardized protocols, and broad clinical applicability, while the same conceptual framework remains generalizable to other neural recording types. This review synthesizes emerging FM approaches for neural decoding and critically examines representative EEG‐based architectures. We highlight three essential design principles: physiology‐aware representation learning that captures oscillatory and dynamic structure, structure‐aware architectures that incorporate spatial and anatomical priors, and interpretability mechanisms that ensure neuroscientific and clinical validity. Although models such as the Patched Brain Transformer, CBraMod, and BrainGPT demonstrate encouraging adaptability, many still inherit objectives from non‐neural domains and underutilize spatial priors such as electrode topology or functional connectivity. While this review focuses on EEG as the most data‐rich and scalable testbed, the same framework can extend to ECoG and intracortical recordings to support unified neural representations across spatial and temporal scales. Fully realizing the potential of neural FMs will require biologically informed objectives, structure‐aware architectures, interpretable representations, and standardized data ecosystems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyBrainModels, NeurologicalHumansMachine LearningAnimals

Stichwörter der Autor:innen

brain–computer interfaceelectroencephalographyfoundation modelneural signal decodingneurophysiological signalrepresentation learning

Autor:innen und Institutionen

  • Department of Brain & Cognitive Sciences, Seoul National University, Seoul, Republic of Korea.
  • Department of Transdisciplinary Medicine, Seoul National University Hospital, Seoul, Republic of Korea.
  • Interdisciplinary Program in Bio-Engineering, Seoul National University, Seoul, Republic of Korea.

ORCID-Profile: Youmin Shin

Zitieren

APA

Kwon, J., & Shin, Y. (2026). Foundation Models for Neural Signal Decoding: EEG‐Centered Perspectives Toward Unified Representations. European Journal of Neuroscience, 63(1). https://doi.org/10.1111/ejn.70376

Vancouver

Kwon J, Shin Y. Foundation Models for Neural Signal Decoding: EEG‐Centered Perspectives Toward Unified Representations. European Journal of Neuroscience. 2026;63(1). doi:10.1111/ejn.70376

BibTeX
@article{Kwon2026,
  author = {Kwon, Jii and Shin, Youmin},
  title = {Foundation Models for Neural Signal Decoding: EEG‐Centered Perspectives Toward Unified Representations},
  journal = {European Journal of Neuroscience},
  year = {2026},
  volume = {63},
  number = {1},
  doi = {10.1111/ejn.70376}
}
Kostenlos starten →