A Hybrid Convolutional, Mamba and Spiking Neural Network Architecture Search for Seizure Prediction
Bo Yu, Chang Li, Rencheng Song, Xiang Liu, Ruobing Qian, Xun Chen · 2026
Read A Hybrid Convolutional, Mamba and Spiking Neural Network Architecture Search for Seizure Prediction by Bo Yu, Chang Li, Rencheng Song, Xiang Liu, Ruobing Qian, Xun Chen (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13624727.txt.
Description
Bo Yu and five colleagues build a search system that designs brain-wave networks for warning of epileptic seizures before they strike. Reading scalp electrical signals, called EEG, is slow by hand, and network design by hand eats time and computing power. Their framework, CMS-NAS, mixes three network styles, convolutional, Mamba, and spiking, and lets an evolution-style search breed candidate designs.
The search scores each candidate on both accuracy and small size, keeping designs light enough for real use. Tests ran on two public data sets and one private set, and the found networks performed on par with strong hand-built rivals. Automatic mixing of network styles, the authors argue, can shorten the path from raw brain signals to a working seizure alarm.
Catalog record
| CREATOR | Bo Yu, Chang Li, Rencheng Song, Xiang Liu, Ruobing Qian, Xun Chen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |