Energy-based Autoregressive Generation for Neural Population Dynamics
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (1) · 309-317
DOI: 10.1609/aaai.v40i1.36992 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Ningling Ge und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Understanding brain function represents a fundamental goal in neuroscience, with critical implications for therapeutic interventions and neural engineering applications. Computational modeling provides a quantitative framework for accelerating this understanding, but faces a fundamental trade-off between computational efficiency and high-fidelity modeling. To address this limitation, we introduce a novel Energy-based Autoregressive Generation (EAG) framework that employs an energy-based transformer learning temporal dynamics in latent space through strictly proper scoring rules, enabling efficient generation with realistic population and single-neuron spiking statistics. Evaluation on synthetic Lorenz datasets and two Neural Latents Benchmark datasets (MC_Maze and Area2_bump) demonstrates that EAG achieves state-of-the-art generation quality with substantial computational efficiency improvements, particularly over diffusion-based methods. Beyond optimal performance, conditional generation applications show two capabilities: generalizing to unseen behavioral contexts and improving motor brain-computer interface decoding accuracy using synthetic neural data. These results demonstrate the effectiveness of energy-based modeling for neural population dynamics with applications in neuroscience research and neural engineering.
Zitieren
APA
Ge, N., Dai, S., Zhu, Y., & Yu, S. (2026). Energy-based Autoregressive Generation for Neural Population Dynamics. Proceedings of the AAAI Conference on Artificial Intelligence, 40(1), 309-317. https://doi.org/10.1609/aaai.v40i1.36992
Vancouver
Ge N, Dai S, Zhu Y, Yu S. Energy-based Autoregressive Generation for Neural Population Dynamics. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(1):309-317. doi:10.1609/aaai.v40i1.36992
BibTeX
@article{Ge2026,
author = {Ge, Ningling and Dai, Sicheng and Zhu, Yu and Yu, Shan},
title = {Energy-based Autoregressive Generation for Neural Population Dynamics},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {1},
pages = {309--317},
doi = {10.1609/aaai.v40i1.36992}
}
EUVIMED