Zero-Shot Neural Priors for Generalizable Cross-Subject and Cross-Task EEG Decoding

Brandone Fonya, BAIMAM BOUKAR JEAN JACQUES, Nchofon Tagha Ghogomu, Pauline Nyaboe, kipngeno koech

Keywords: Brain Decoding, Electroencephalogram, Transfer learning

TL;DR: Work captures domain- and subject-invariant neural representations to enable behavioral prediction

Abstract: The development of generalizable electroencephalography (EEG) decoding models is essential for robust brain-computer interfaces (BCI) and objective neural biomarkers in mental health. Conventional approaches have been hindered by poor cross-subject and cross-task generalization, owing to high inter-subject variability and non-stationary neural signals. We address this challenge with a zero-shot cross-subject decoding framework on the large-scale Healthy Brain Network dataset, benchmarking a convolutional neural network baseline, a hybrid LSTM, and a Transformer-based foundation model. To adapt the Transformer for regression while averting catastrophic forgetting, we propose a novel progressive unfreezing strategy. The baseline yielded an $n\mathrm{RMSE}$ of $0.9991$, whereas our fine-tuned Transformer achieved $0.9799$ on unseen subjects.This work establishes scalable, calibration-free EEG decoding for computational psychiatry and behavioral prediction.

Primary Subject Area: Transfer Learning and Domain Adaptation

Secondary Subject Area: Unsupervised Learning and Representation Learning

Registration Requirement: Yes

Reproducibility: https://github.com/Nchofon/neuronium

Visa & Travel: No

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 401