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.

在过去的几十年里，记录大量神经元的能力（例如，多电极 阵列，神经像素，钙成像）呈指数级增长，有希望的新途径，了解 大脑这些数据有希望提供一个定性的不同观点的活动内和跨大脑 这一工作将比以前可能的工作范围更广，但需要开发先进的分析工具。一 动力系统的工具提供了一个自然的框架，它提供了揭示协调的方法。 在记录的神经元的互连网络中表达的时变激活模式， 描述这些模式与行为的关系。这一框架提供了基本的新见解， 这些皮层回路中的信息处理，包括那些潜在的运动、感觉和认知回路 流程.然而，以前的分析方法来揭示动态通常已经开发， 在特定的大脑区域进行测试，针对有限的行为，在有限的行为环境中。具有讽刺意味的是， 对于这些方法，需要设置或学习10^5个参数，并需要仔细调优以正确地 功能然而，大脑并不是同质的，目前还不清楚这些方法能在多大程度上用于 概括到各种大脑区域和行为，更不用说那些不熟悉 方法此外，假设大脑的动力来自独立的、孤立的区域， 过于简单化。显然，知觉、认知和运动功能都依赖于分布在大脑中的活动。 多个相互作用的大脑区域，每个区域可能都有不同的动态。区域之间的通信是 这是一个以灵活功能为基础的动态过程。人们越来越认识到，人口动态是 特别是为了支持区域间的互动，迫切需要有方法来准确地 揭示相互作用区域之间的动态。 我们将通过开发一种强大的 新的开源工具包，用于在高度发散的大脑中自动发现神经种群动态 地区此外，我们将用新的神经网络架构扩展这个工具包，以模拟 互动领域。我们的方法，动态系统ID工具包（DSID），将支持准确， 直接应用于来自不同大脑区域和行为的数据，而不需要更多的专业知识， 基础设施建设。DSID将利用顺序自动编码器（SAE），强大而灵活的深度学习 使用递归神经网络来表征非线性动态系统的架构。我们将验证 使用先前收集的和新的多电极记录数据的组合的DSID的普遍性 包括运动、感觉和认知皮层。随着其发展和 在我们的实验室验证，我们将努力传播他们在适当的研究社区， 我们期望它们将得到进一步的发展，应用于更广泛的大脑区域和行为。