Developing artificial neural network tools for cognitive modeling

开发用于认知建模的人工神经网络工具

• 批准号: 10641215
• 负责人: Anne G.E. Collins
• 金额: $ 22.85万
• 依托单位: UNIVERSITY OF CALIFORNIA BERKELEY
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-04-01 至 2025-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10641215
• 关键词: Animals; Arbitration; Bayesian Analysis; Behavior; Behavioral; Brain; Brain Diseases; Bypass; Categories; Cognition; Cognitive; Communities; Complex; Computational Technique; Computer Models; Custom; Data; Dependence; Diffusion; Environment; Equation; Event; Exhibits; Goals; Human; Impairment; Individual; Individual Differences; Knowledge; Learning; Mathematics; Mental disorders; Methodology; Methods; Modeling; Modernization; Motor; Neurodegenerative Disorders; Neurosciences; Outcome; Output; Participant; Patients; Performance; Play; Population; Psychiatry; Psychological reinforcement; Research; Research Personnel; Rewards; Role; Sampling; Techniques; Testing; Training; Translating; Translations; Uncertainty; Work; artificial neural network; cognitive benefits; cognitive task; coping; deep neural network; information processing; interest; mathematical model; neural; neural network; neurotransmission; novel; predictive modeling; prospective; simulation; supervised learning; theories; tool

Project Summary/Abstract Mathematical modeling is an essential tool to study the brain, behavior and cognition. Computational cognitive models state with simple mathematical equations how the brain may be manipulating information that supports how humans and animals interpret the world around them, make choices and adapt to new environments or events. Researchers can use computational cognitive models to quantitatively test the theories embedded in the models, by comparing model predictions with behavioral and neural data. Models also often have meaningful parameters that can be tuned to reflect how specific information is used, for example how much participants weigh prospective gains vs. losses in decisions, how willing participants are to explore new information vs. exploit the information they already have, or how confident they need to be before committing to a decision. In the context of psychiatric and neuro-degenerative diseases, computational modelers can ask whether models fit patients' behavior/neural activity differently than healthy controls, thereby explaining impairments as a difference in information processing; or whether they exhibit different parameters for the same models, showing different weighing of information. Thus, computational modeling provides important quantitative tools to understand how brain disease impacts behavior and cognition. However, such research requires statistical tools to quantitatively relate models to data - that is, to identify which models and which parameters explain the data best. Existing tools mostly rely on computing the likelihood of the data under the model, and are very powerful for a specific class of models. However, they leave out a much broader class of models for which the likelihood is too complex to compute. This class of models includes many simple and relevant models that embody reasonable theories of cognition, but these models are currently unexplored, because researchers lack the tools required to relate them to data. The goal of this proposal is to develop new tools for this class of models, using modern supervised machine learning techniques (with deep neural networks) that bypass the need to compute the likelihood, but do not require advanced expertise in ap- plied mathematics and are broadly generalizable to the whole class of models that are currently inaccessible to existing techniques. Specifically, we will develop tools to 1) identify which of multiple models explain a partici- pant's data better, 2) identify the value of model parameters that best explain a participant's data, and 3) infer how the model variables generated the participant's behavior, enabling us to relate these variables to brain data. This research will vastly increase the potential reach of computational techniques in neuroscience, enabling researchers to consider theories that are currently discarded for lack of tools. This is an important step toward broadening our understanding of mental illness and brain diseases.

项目概要/摘要 数学建模是研究大脑、行为和认知的重要工具。 模型用简单的数学方程说明大脑如何操纵支持信息 人类和动物如何解释周围的世界、做出选择并适应新环境或 研究人员可以使用计算认知模型来定量测试嵌入的理论。 模型，通过将模型预测与行为和神经数据进行比较。 可以调整参数以反映特定信息的使用方式，例如使用了多少信息 权衡决策中的预期收益与损失，探索新信息与探索新信息的意愿如何。 利用他们已有的信息，或者他们在做出决定之前需要有多大的信心。 在精神疾病和神经退行性疾病的背景下，计算建模者可以询问模型是否适合 患者的行为/神经活动与健康对照组不同，从而将损伤解释为差异 在信息处理方面；或者对于相同的模型，它们是否表现出不同的参数，表现出不同的结果。 因此，计算模型提供了重要的定量工具来理解如何衡量信息。 脑部疾病影响行为和认知。 然而，此类研究需要统计工具来定量地将模型与数据联系起来——也就是说，识别 哪些模型和哪些参数可以最好地解释数据？现有工具主要依赖于计算可能性。 模型下的数据，并且对于特定类别的模型非常强大，但是，它们遗漏了一个。 这类模型包括更广泛的类别，其可能性太复杂而无法计算。 许多简单且相关的模型体现了合理的认知理论，但这些模型目前 尚未探索，因为研究人员缺乏将它们与数据联系起来所需的工具。 使用现代监督机器学习技术（深度学习）为此类模型开发新工具 神经网络）绕过计算可能性的需要，但不需要应用方面的高级专业知识 复合数学，并且可以广泛推广到目前无法访问的整个模型类别 具体来说，我们将开发工具来 1）识别多个模型中的哪一个可以解释某个参与者。 更好地解释裤子的数据，2) 确定最能解释参与者数据的模型参数值，以及 3) 推断 模型变量如何产生参与者的行为，使我们能够将这些变量与大脑数据联系起来。 这项研究将极大地增加计算技术在神经科学中的潜在影响力，使 研究人员考虑目前因缺乏工具而被抛弃的理论，这是迈向这一目标的重要一步。 拓宽我们对精神疾病和脑部疾病的理解。