Neural Decoding as Cognitive Inference
Abstract
The brain maintains stable cognition despite continuously changing neural activity. How to extract stable cognitive states from variable neural observations remains a central problem in neural decoding. Existing neural decoding methods map neural observations to predefined external labels based on the stimulus-response principle, often capturing recording-specific spurious correlations. Inspired by how the brain infers the world, and specifically by Bayesian brain theory, we recast neural decoding as cognitive inference constrained by brain-intrinsic priors, yielding high-level meta-neural semantic representations. In decoding experiments spanning five neural recording modalities and three cognitive domains (motor, perception and internal mentation), our cognitive inference method reorganized the geometry of neural observation representations, yielding meta-neural semantic representations that exhibited consistent geometric relationships across cognitive tasks and enabled the recovery of stable cognitive states from variable neural observations. Our work provides an account of how the brain maintains relatively stable cognition despite continual changes in the external environment. Cognitive stability is sustained through cognitive inference from changing neural activity, without requiring fixed neural activity patterns.
Related
- Generalizable neural decoding for clinically scalable brain-computer interfaces.
- T-SNN: Temporal Simplicial Neural Network for EEG Decoding
- Biophysically constrained learning from healthy neural priors improves motor decoding in pathological cortical networks
- Speech Restoration & Mental Surveillance as Conflicting Ethical Concerns in Neural Speech-Decoding Research.
- Individual Differences in Neural Decoding Are Stable but Instrument Dependent
BibTeX
@misc{guo2026neural,
title = {{Neural Decoding as Cognitive Inference}},
author = {Yi Guo and Changhong Jing and Yong Hu and Yan Liu and Michael K. P. Ng and Shanshan Wang and Shuqiang Wang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.11923},
eprint = {2610.11923},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.11923},
}
RIS
TY - UNPB
TI - Neural Decoding as Cognitive Inference
AU - Yi Guo
AU - Changhong Jing
AU - Yong Hu
AU - Yan Liu
AU - Michael K. P. Ng
AU - Shanshan Wang
AU - Shuqiang Wang
PY - 2026
DA - 2026/10/08
PB - arXiv
DO - 10.48550/arxiv.2610.11923
UR - https://arxiv.org/abs/2610.11923
AB - The brain maintains stable cognition despite continuously changing neural activity. How to extract stable cognitive states from variable neural observations remains a central problem in neural decoding. Existing neural decoding methods map neural observations to predefined external labels based on the stimulus-response principle, often capturing recording-specific spurious correlations. Inspired by how the brain infers the world, and specifically by Bayesian brain theory, we recast neural decoding as cognitive inference constrained by brain-intrinsic priors, yielding high-level meta-neural semantic representations. In decoding experiments spanning five neural recording modalities and three cognitive domains (motor, perception and internal mentation), our cognitive inference method reorganized the geometry of neural observation representations, yielding meta-neural semantic representations that exhibited consistent geometric relationships across cognitive tasks and enabled the recovery of stable cognitive states from variable neural observations. Our work provides an account of how the brain maintains relatively stable cognition despite continual changes in the external environment. Cognitive stability is sustained through cognitive inference from changing neural activity, without requiring fixed neural activity patterns.
ER -