时间演化动力系统用于学习小鼠视觉神经活动的潜在表征
Time-Evolving Dynamical System for Learning Latent Representations of Mouse Visual Neural Activity
AI总结：
提出时间演化视觉动力系统（TE-ViDS），一种序列潜在变量模型，通过分解神经活动为随时间演化的低维表征并应用对比学习，在小鼠视觉皮层数据上实现最佳解码性能，揭示神经动力学。
摘要：
利用潜在变量模型（LVM）寻求高质量表征以揭示神经活动与行为或感觉刺激之间的内在关联，已引起广泛关注。在生物视觉系统的研究中，自然视觉刺激本质上是高维且随时间变化的，导致视觉神经活动内部出现复杂的动力学特性。然而，大多数关于LVM的研究并未明确考虑神经时间关系。为应对这些情况，我们提出了时间演化视觉动力系统（TE-ViDS），这是一种序列LVM，将神经活动分解为随时间演化的低维潜在表征。为了更好地使模型与视觉神经活动的特性对齐，我们将潜在表征分为两部分，并应用对比学习来塑造它们。在合成数据集和小鼠视觉皮层的真实神经数据集上进行的大量实验表明，TE-ViDS在自然场景/电影上实现了最佳解码性能，提取出可解释的潜在轨迹，揭示了清晰的潜在神经动力学，并为受试者之间以及皮层区域之间视觉信息处理的差异提供了新的见解。总之，TE-ViDS在从视觉神经活动中提取刺激相关嵌入方面表现出显著能力，并有助于理解视觉处理机制。我们的代码可在 https://github.com/Grasshlw/Time-Evolving-Visual-Dynamical-System 获取。
英文摘要：
Seeking high-quality representations with latent variable models (LVMs) to reveal the intrinsic correlation between neural activity and behavior or sensory stimuli has attracted much interest. In the study of the biological visual system, naturalistic visual stimuli are inherently high-dimensional and time-dependent, leading to intricate dynamics within visual neural activity. However, most work on LVMs has not explicitly considered neural temporal relationships. To cope with such conditions, we propose Time-Evolving Visual Dynamical System (TE-ViDS), a sequential LVM that decomposes neural activity into low-dimensional latent representations that evolve over time. To better align the model with the characteristics of visual neural activity, we split latent representations into two parts and apply contrastive learning to shape them. Extensive experiments on synthetic datasets and real neural datasets from the mouse visual cortex demonstrate that TE-ViDS achieves the best decoding performance on naturalistic scenes/movies, extracts interpretable latent trajectories that uncover clear underlying neural dynamics, and provides new insights into differences in visual information processing between subjects and between cortical regions. In summary, TE-ViDS is markedly competent in extracting stimulus-relevant embeddings from visual neural activity and contributes to the understanding of visual processing mechanisms. Our codes are available at https://github.com/Grasshlw/Time-Evolving-Visual-Dynamical-System.
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。
