arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.17606cs.LGcs.AI
收藏

基于能量的自回归生成用于神经群体动力学

Energy-based Autoregressive Generation for Neural Population Dynamics

Ningling Ge 1,2,3(Ge Ningling 机构1, 机构2, 机构3);Sicheng Dai 1,2,3,4(Dai Sicheng 机构1, 机构2, 机构3, 机构4);Yu Zhu 1,2,3,4(Zhu Yu 机构1, 机构2, 机构3, 机构4);Shan Yu 1, 3(Yu Shan 机构1, 机构3)

Ningling Ge, Sicheng Dai, Yu Zhu, Shan Yu

AI总结:

本文提出基于能量的自回归生成框架,用于高效生成神经群体动态,展示其在生成质量和计算效率上的优势。

摘要:

理解大脑功能是神经科学中的基本目标,对治疗干预和神经工程应用具有关键意义。计算建模提供了一个定量框架来加速这一理解,但面临着计算效率和高保真建模之间的根本权衡。为了解决这一限制,我们引入了一个新的基于能量的自回归生成(EAG)框架,该框架通过严格正确的评分规则在潜在空间中使用能量基于的变压器学习时间动态,从而实现高效生成,具有真实的群体和单神经元脉冲统计特性。在合成洛伦兹数据集和两个神经潜在基准数据集(MC_Maze和Area2_bump)上的评估表明,EAG在生成质量上达到了最先进的水平,并在计算效率上有显著的改进,特别是在与扩散方法相比时。除了最佳性能外,条件生成应用显示了两种能力:能够推广到未见的行为上下文,并利用合成神经数据提高运动脑机接口解码的准确性。这些结果展示了基于能量的建模在神经群体动力学中的有效性,并在神经科学研究和神经工程中具有应用。代码可在https://github.com/NinglingGe/Energy-based-Autoregressive-Generation-for-Neural-Population-Dynamics上获得。

英文摘要:

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. Code is available at https://github.com/NinglingGe/Energy-based-Autoregressive-Generation-for-Neural-Population-Dynamics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑