Building Interpretable, Trust-worthy Systems for Neural Signal Decoding
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41531-41533
DOI: 10.1609/aaai.v40i48.42330 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Hua Xu.
Abstract (Originalsprache)
While deep learning excels at decoding neural signals, the opacity of state-of-the-art models limits their scientific utility and clinical trustworthiness. We propose a research that bridges this gap by integrating high-performance architectures—specifically Transformers and Graph Neural Networks—with mechanistic interpretability and neuro-symbolic reasoning. This proposal aims to uncover verifiable mappings between artificial computational circuits and biological dynamics without compromising decoding accuracy. Validated through rigorous benchmarking and wet-lab experiments, this work establishes a foundation for transparent brain-computer interfaces and accelerates fundamental neuroscience research.
Zitieren
APA
Xu, H. (2026). Building Interpretable, Trust-worthy Systems for Neural Signal Decoding. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41531-41533. https://doi.org/10.1609/aaai.v40i48.42330
Vancouver
Xu H. Building Interpretable, Trust-worthy Systems for Neural Signal Decoding. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41531-41533. doi:10.1609/aaai.v40i48.42330
BibTeX
@article{Xu2026,
author = {Xu, Hua},
title = {Building Interpretable, Trust-worthy Systems for Neural Signal Decoding},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41531--41533},
doi = {10.1609/aaai.v40i48.42330}
}
EUVIMED