RI: Small: Integrating Flexible Normalization Models of Visual Cortex into Deep Neural Networks

RI：小：将视觉皮层的灵活标准化模型集成到深度神经网络中

基本信息

批准号：
1715475
负责人：
Odelia Schwartz
金额：
$ 35万
依托单位：
University of Miami
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：
2017-09-01 至 2021-08-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1715475&HistoricalAwards=false
关键词：
RI Small Integrating Flexible Normalization

项目摘要

Recent advances in artificial intelligence models of deep neural networks have led to tremendous progress in artificial systems that recognize objects in scenes, and in a host of other applications such as speech recognition, and robotics. Although deep neural networks often incorporate computations inspired by the brain, these have typically been applied in a fairly simple and restrictive manner, rather than based on more principled models of neural processing in the brain. Using vision as a paradigmatic example, this project proposes that artificial systems can benefit from integrating approaches that have been developed in biological models of neural processing of scenes. The biological models make use of contextual flexibility, whereby neurons are influenced in a rich way by the image structure that spatially surrounds a given object or feature. This flexibility is expected to improve task performance in deep neural networks, and to impact development of artificial systems that are more compatible with human cognition. The resulting framework, with its deep architecture spanning multiple layers of processing, will, in turn, make predictions about neural processing in the brain, which will impact the neuroscience and cognitive science communities. This project focuses specifically on normalization, a nonlinear computation that is ubiquitous in the brain, and that has been shown to benefit task performance in deep neural networks. The project will develop more principled strategies for determining normalization in deep convolutional neural networks. The main focus will be on learning a form of flexible normalization based on scene statistics models of visual cortex. In this framework, normalization is recruited only to the degree that a visual input is inferred to contain statistical dependencies across space. Performance will be tested for classification and segmentation on large-scale image databases, and will also target tasks more suited to mid-level vision such as figure/ground judgment. This will result in better understanding of normalization nonlinearities in deep convolutional networks, and the implications of flexible normalization for task performance and generalization compared to other forms of normalization. Biologically, normalization is poorly understood beyond primary visual cortex. The models developed will help shed light on the equivalence of this inference for middle cortical areas, and make predictions about what image structure leads to recruitment of normalization. This project will also include launching of an interdisciplinary Deep Learning Discussion Group.

深度神经网络人工智能模型的最新进展导致识别场景中物体的人工系统以及语音识别和机器人等许多其他应用取得了巨大进步。尽管深度神经网络通常包含受大脑启发的计算，但这些计算通常以相当简单和限制性的方式应用，而不是基于大脑中更原则的神经处理模型。该项目以视觉为范例，提出人工系统可以从场景神经处理生物模型中开发的集成方法中受益。生物模型利用上下文灵活性，神经元受到空间上围绕给定对象或特征的图像结构的丰富影响。这种灵活性有望提高深度神经网络的任务性能，并影响与人类认知更兼容的人工系统的开发。由此产生的框架，其深层架构跨越多个处理层，反过来，将对大脑中的神经处理进行预测，这将影响神经科学和认知科学界。该项目特别关注归一化，这是一种在大脑中普遍存在的非线性计算，并且已被证明有利于深度神经网络的任务性能。该项目将开发更有原则的策略来确定深度卷积神经网络的标准化。主要重点是学习一种基于视觉皮层场景统计模型的灵活标准化形式。在这个框架中，归一化仅在视觉输入被推断包含跨空间的统计依赖性的程度上进行。性能将在大规模图像数据库上进行分类和分割测试，还将针对更适合中级视觉的任务，例如图形/地面判断。这将有助于更好地理解深度卷积网络中的归一化非线性，以及与其他形式的归一化相比灵活归一化对任务性能和泛化的影响。从生物学角度来看，除了初级视觉皮层之外，人们对正常化知之甚少。开发的模型将有助于阐明这种推断对于中皮层区域的等价性，并预测哪些图像结构会导致标准化的招募。该项目还将包括启动跨学科深度学习讨论组。