RI: Medium: Collaborative Research: Incorporating Biologically-Motivated Circuit Motifs into Large-Scale Deep Neural Network Models of the Brain

RI：中：协作研究：将生物驱动的电路基序纳入大脑的大规模深度神经网络模型

• 批准号: 1704938
• 负责人: Kenneth Miller
• 金额: $ 52.5万
• 依托单位: Columbia University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-10-01 至 2021-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1704938&HistoricalAwards=false
• 关键词: RI; Medium; Collaborative; Research; Incorporating

This project studies the effects of incorporating, into deep neural networks for visual processing, several heretofore unincorporated features of biological visual cortical circuits. Deep neural networks are artificial circuits loosely inspired by the brain's cerebral cortex. Their abilities to solve complex problems, such as recognizing objects in visual scenes, have revolutionized artificial intelligence and machine learning in recent years. The hierarchy of layers in a deep network trained for visual object recognition also provides the best existing models of the hierarchy of areas in the visual cortex implicated in object recognition (the "ventral stream"). This project seeks to understand whether and how incorporating additional features of brain circuits may (1) improve machine learning performance, particularly on tasks that are more challenging than those typically studied; and (2) yield improved models of visual cortex. Improving the performance of deep networks would yield great benefits across wide swaths of society and industry that are impacted by advances in artificial intelligence. Improved models of visual cortex will advance understanding of cortical function, which may lead to significant further benefits for understanding normal mental functioning and perception and their potential enhancement, as well as mental illness and perceptual and cognitive deficits. Deep networks currently achieve their success using almost purely feedforward processing. Yet the visual cortical ventral stream that helped inspire deep networks also uses massive recurrent processing within each area as well as feedback connections from higher areas to lower areas and "bypass" connections from lower areas to areas multiple steps higher in the hierarchy. Deep networks also use "neurons" that can either excite or inhibit different neurons that they project to, whereas biological neurons are exclusively excitatory or inhibitory. This project will incorporate feedback and bypass connections into deep networks, as well as local recurrent processing in networks of separate excitatory and inhibitory neurons. Recent work by the investigators has shown how local recurrent processing explains a number of nonlinear visual cortical operations often summarized as "normalization." Simple forms of normalization currently used in deep networks maintain activities in an appropriate dynamic range, but the biological forms of normalization involve interactions between different stimulus features and locations in determining neural responses, which may have important computational roles e.g. in parsing visual scenes. The performance of deep networks incorporating these features will be assayed on a variety of visual tasks and as models of ventral stream neural data and human psychophysical data, and compared to performance of existing deep net models.

该项目研究了纳入深层神经网络进行视觉处理的效果，这些源自生物视觉皮层电路的几种迄今未合并的特征。深度神经网络是受大脑大脑皮质的启发的人造电路。他们解决复杂问题的能力，例如在视觉场景中识别对象，近年来彻底改变了人工智能和机器学习。在训练视觉对象识别的深层网络中，图层的层次结构还提供了与对象识别有关的视觉皮层区域层次结构的最佳现有模型（“腹流”）。该项目试图了解大脑电路的其他功能以及如何（1）提高机器学习绩效，尤其是在比通常研究的任务更具挑战性的任务上； （2）产生改进的视觉皮层模型。提高深层网络的绩效将在人工智能进步影响的社会和行业的广泛范围内带来巨大的好处。改进的视觉皮层模型将提高人们对皮质功能的理解，这可能会带来明显的进一步好处，以了解正常的心理功能和感知及其潜在的增强，以及精神疾病，感知和认知缺陷。深层网络目前使用几乎纯粹的前馈处理实现了成功。然而，有助于激发深层网络的视觉皮质腹流也使用了每个区域内的大量经常性处理，以及从较高区域到较低区域的反馈连接，以及从较低区域到层次结构中较高的区域的“旁路”连接。深网还使用“神经元”可以激发或抑制其投影到的不同神经元，而生物神经元仅兴奋或抑制性。该项目将将反馈和旁路连接纳入深网，以及在单独的兴奋性和抑制性神经元网络中的局部反复处理。研究人员最近的工作表明，局部经常性处理如何解释了许多非线性视觉皮质操作通常总结为“归一化”。当前在深网中使用的简单形式的正常化形式将活动保持在适当的动态范围内，但是标准化的生物学形式涉及不同刺激特征和位置之间的相互作用，以确定神经反应，这可能具有重要的计算角色，例如在解析视觉场景中。结合这些功能的深网的性能将在各种视觉任务以及腹溪流神经数据和人体心理物理数据的模型上进行测定，并将其与现有深网模型的性能进行比较。

项目成果

Do Biologically-Realistic Recurrent Architectures Produce Biologically-Realistic Models?

生物学真实的循环架构是否能产生生物学真实的模型？

• DOI: 10.32470/ccn.2019.1175-0
• 发表时间: 2019
• 期刊: 2019 Conference on Cognitive Computational Neuroscience
• 作者: Lindsay, Grace;Moskovitz, Theodore;Yang, Guangyu Robert;Miller, Kenneth
• 通讯作者: Miller, Kenneth

A deep learning framework for neuroscience

• DOI: 10.1038/s41593-019-0520-2
• 发表时间: 2019-11-01
• 期刊: NATURE NEUROSCIENCE
• 影响因子: 25
• 作者: Richards, Blake A.;Lillicrap, Timothy P.;Kording, Konrad P.
• 通讯作者: Kording, Konrad P.