Estimating the Event-Related Potential from Few EEG Trials

2025-11-28

AI Summary

Traditional ERP estimation relies heavily on averaging numerous EEG trials, making it impractical in low-resource settings. To address this, we propose EEG2ERP—the first deep learning framework designed for cross-subject zero-shot ERP estimation. Built upon an uncertainty-aware autoencoder, EEG2ERP introduces a novel variance decoder and a guided dual-decoder architecture to enable end-to-end EEG-to-ERP mapping while explicitly modeling estimation uncertainty. Evaluated on multiple public EEG datasets, EEG2ERP achieves stable, high-fidelity ERP waveform reconstruction using only 1–5 trials—significantly outperforming conventional trial averaging and state-of-the-art robust estimation methods (p < 0.01). To our knowledge, this is the first work to enable reliable cross-subject ERP generalization from extremely few trials. EEG2ERP establishes a new paradigm for rapid clinical ERP assessment and real-time ERP analysis in portable brain–computer interfaces.

Technology Category

• Intelligent Robots: State Estimation
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Event-related potentials (ERP) are measurements of brain activity with wide applications in basic and clinical neuroscience, that are typically estimated using the average of many trials of electroencephalography signals (EEG) to sufficiently reduce noise and signal variability. We introduce EEG2ERP, a novel uncertainty-aware autoencoder approach that maps an arbitrary number of EEG trials to their associated ERP. To account for the ERP uncertainty we use bootstrapped training targets and introduce a separate variance decoder to model the uncertainty of the estimated ERP. We evaluate our approach in the challenging zero-shot scenario of generalizing to new subjects considering three different publicly available data sources; i) the comprehensive ERP CORE dataset that includes over 50,000 EEG trials across six ERP paradigms from 40 subjects, ii) the large P300 Speller BCI dataset, and iii) a neuroimaging dataset on face perception consisting of both EEG and magnetoencephalography (MEG) data. We consistently find that our method in the few trial regime provides substantially better ERP estimates than commonly used conventional and robust averaging procedures. EEG2ERP is the first deep learning approach to map EEG signals to their associated ERP, moving toward reducing the number of trials necessary for ERP research. Code is available at https://github.com/andersxa/EEG2ERP

Problem

• Estimating ERPs from limited EEG trials using deep learning
• Modeling ERP uncertainty with bootstrapped training and variance decoding
• Improving zero-shot generalization across subjects and datasets

Innovation

• Uncertainty-aware autoencoder maps EEG trials to ERP
• Bootstrapped training targets model ERP estimation uncertainty
• Separate variance decoder captures ERP variability from EEG