Decision Confidence Neuron in Echo State Network for Continual Evaluation of EEG Motor Imagery Classification Quality
- 1Ulster University
Abstract
Echo state networks (ESNs) are efficient, neuro-inspired computational frameworks well suited to time-series data. However, ESN decision confidence is typically quantified in limited ways. We propose an explicit decision-confidence readout neuron, trained from decision readout outputs, to continuously monitor confidence as decisions form. In a simulated decision task, confidence activity increased with stimulus strength, linking greater discriminability to higher confidence. We then evaluated the model on EEG-based motor imagery classification, showing that confidence activity increased with decision accuracy and discriminated correct from error decisions, particularly in higher-performing participants, reflecting human-like metacognition. Overall, this approach enables continual monitoring of decision confidence, supporting more trustworthy ESN decisions, particularly in biomedical applications.
Related
- Neural latent representation of implicit perceptual decision confidence signatures from brain-wide intracranial EEG
- Taxonova: Deep learning enables fast and confidence-aware microbiome species-level amplicon classification
- Longitudinal clinical impact of dynamic variant re-classification on reproductive decision-making: a 3-year case study
- Confidence-guided integration of otoscopy videos and tympanometry for middle ear disease diagnosis: A multi-center otoscopy study with external paired-cohort evaluation
- Application of Bayesian-Derived Gene Interaction Network and Subnetwork for Classification of Idiopathic Parkinson Disease with Biomarkers
BibTeX
@misc{lemoine2026decision,
title = {{Decision Confidence Neuron in Echo State Network for Continual Evaluation of EEG Motor Imagery Classification Quality}},
author = {E. Lemoine and B. Lenfesty and U. K. N. Mudavath and S. Bhattacharyya and K. Wong-Lin},
howpublished = {bioRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.31.748424},
url = {https://www.biorxiv.org/content/10.64898/2026.08.31.748424v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Decision Confidence Neuron in Echo State Network for Continual Evaluation of EEG Motor Imagery Classification Quality
AU - E. Lemoine
AU - B. Lenfesty
AU - U. K. N. Mudavath
AU - S. Bhattacharyya
AU - K. Wong-Lin
PY - 2026
DA - 2026/08/31
PB - bioRxiv
DO - 10.64898/2026.08.31.748424
UR - https://www.biorxiv.org/content/10.64898/2026.08.31.748424v1
AB - Echo state networks (ESNs) are efficient, neuro-inspired computational frameworks well suited to time-series data. However, ESN decision confidence is typically quantified in limited ways. We propose an explicit decision-confidence readout neuron, trained from decision readout outputs, to continuously monitor confidence as decisions form. In a simulated decision task, confidence activity increased with stimulus strength, linking greater discriminability to higher confidence. We then evaluated the model on EEG-based motor imagery classification, showing that confidence activity increased with decision accuracy and discriminated correct from error decisions, particularly in higher-performing participants, reflecting human-like metacognition. Overall, this approach enables continual monitoring of decision confidence, supporting more trustworthy ESN decisions, particularly in biomedical applications.
ER -