Robust modeling of within- and across-area population dynamics using recurrent neural networks

使用循环神经网络对区域内和跨区域人口动态进行稳健建模

• 批准号: 10263644
• 负责人: Lee Miller
• 金额: $ 131.25万
• 依托单位: EMORY UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-15 至 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10263644
• 关键词: 3-Dimensional; Address; Advanced Development; Architecture; Area; Behavior; Behavioral; Brain; Calcium; Code; Cognitive; Communication; Communities; Complex; Computer software; Data; Data Analyses; Data Collection; Data Set; Development; Documentation; Drops; Electrodes; Forearm; Image; Individual; Infrastructure; Locomotion; Mediating; Methods; Modeling; Modernization; Monitor; Monkeys; Motor; Motor Cortex; Movement; Muscle; Neurons; Nonlinear Dynamics; Online Systems; Pattern; Population; Population Dynamics; Process; Research; Research Personnel; Scheme; Sensory; Sensory Process; Somatosensory Cortex; Source Code; Structure; Testing; Time; Validation; Variant; Work; Wrist; analytical tool; autoencoder; base; cloud based; cognitive process; data standards; data tools; data visualization; deep learning; dynamic system; flexibility; frontal lobe; grasp; high dimensionality; information processing; insight; multi-electrode arrays; multidimensional data; neural network architecture; open source; open source tool; recurrent neural network; relating to nervous system; somatosensory; stem; tool

Over the past several decades, the ability to record from large populations of neurons (e.g., multi-electrode arrays, neuropixels, calcium imaging) has increased exponentially, promising new avenues for understanding the brain. These data have the promise to provide a qualitatively different view of activity within and across brain areas than was previously possible, but the effort will require the development of advanced analytical tools. One natural framework is provided by the tools of dynamical systems, which offer the means to uncover coordinated time-varying activation patterns expressed across an interconnected network of recorded neurons, and to characterize how these patterns relate to behavior. This framework has provided fundamental new insights into information processing in these cortical circuits, including those underlying motor, sensory, and cognitive processes. However, previous analytical approaches to uncovering dynamics have typically been developed and tested in specific brain areas, for limited behaviors, in restricted behavioral settings. Ironically, it is not unusual for these methods to have 10^5 parameters that need to be set or learned, and require careful tuning to properly function. Yet the brain is not homogenous, and it is unclear how well these approaches can be made to generalize to a variety of brain areas and behaviors, let alone by researchers who are not intimately familiar with the methods. Further, assuming that the brain's dynamics stem from independent, isolated areas is a vast oversimplification. Clearly, perceptual, cognitive, and motor functions all rely on activity distributed across multiple, interacting brain areas, each of which likely has distinct dynamics. Communication between areas is a dynamic process that underlies flexible function. There is growing recognition that population dynamics are specifically structured to support inter-area interaction, and an immediate need for methods to accurately uncover dynamics between interacting areas. We will address the challenge of generalized applicability to diverse brain areas by developing a powerful new open-source toolkit for automated discovery of neural population dynamics, within highly divergent brain areas. Further, we will extend this toolkit with new neural network architectures to model the dynamics between interacting areas. Our approach, the Dynamical Systems ID toolkit (DSID), will support accurate and straightforward application to data from different brain areas and behaviors without requiring great expertise or infrastructure setup. DSID will leverage sequential autoencoders (SAEs), powerful and flexible deep learning architectures that use recurrent neural networks to characterize nonlinear dynamical systems. We will validate the generalizability of DSID using a combination of previously-collected and new multi-electrode recording data from monkeys, including motor, sensory, and cognitive areas of cortex. Following their development and validation in our labs, we will work to disseminate them throughout the appropriate research communities where we expect they will be further developed with application to an even broader range of brain areas and behaviors.

在过去的几十年中，能够记录大量神经元的能力（例如，多电极 阵列，神经质子，钙成像）呈指数增加，有望理解新的途径 大脑。这些数据有望在大脑内部和整个大脑中提供不同的活动观点 领域比以前可能的领域，但努力将需要开发高级分析工具。一 自然框架由动态系统的工具提供，该工具提供了揭露协调的手段 在记录的神经元的互连网络上表达的时变激活模式， 表征这些模式与行为的关系。该框架为 这些皮质电路中的信息处理，包括那些基础电动机，感觉和认知能力的信息 过程。但是，通常已经开发了以前发现动态的分析方法，并且 在特定的大脑区域，有限的行为，行为环境中进行测试。具有讽刺意味的是，这并不罕见 要使这些方法具有需要设置或学习的10^5个参数，并且需要仔细的调整才能正确调整 功能。然而大脑不是同质的，目前尚不清楚这些方法如何使 概括到各种大脑区域和行为，更不用说不熟悉的研究人员 方法。此外，假设大脑的动态源于独立的，孤立的区域是一个广阔的地方 简单化。显然，感知，认知和运动功能都取决于分布在跨越的活动 多个相互作用的大脑区域，每个区域都可能具有不同的动态。区域之间的交流是 动态过程是灵活函数的基础。人们越来越认识到人口动态是 专门为支持区域间相互作用而进行的特定结构，并立即需要进行准确的方法 发现相互作用区域之间的动态。 我们将通过开发强大的强大 在高度不同的大脑内，用于自动发现神经人口动态的新开源工具包 区域。此外，我们将使用新的神经网络体系结构扩展此工具包 互动区域。我们的方法，动态系统ID工具包（DSID），将支持准确的 直接应用于来自不同大脑领域和行为的数据，而无需大量专业知识或 基础架构设置。 DSID将利用顺序自动编码器（SAE），强大而灵活的深度学习 使用复发神经网络来表征非线性动力学系统的体系结构。我们将验证 使用先前收集和新的多电极记录数据的组合DSID的概括性 来自猴子，包括运动，感觉和认知区域。遵循他们的发展和 在我们的实验室验证中，我们将努力在适当的研究社区中传播它们 我们预计，随着将它们应用于更广泛的大脑区域和行为，它们将进一步发展。