RI: Small: Understanding the Inductive Bias Caused by Invariance and Multi Scale in Neural Networks

RI：小：理解神经网络中不变性和多尺度引起的归纳偏差

• 批准号: 2213335
• 负责人: David Jacobs
• 金额: $ 60万
• 依托单位: University of Maryland, College Park
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-01 至 2025-08-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2213335&HistoricalAwards=false
• 关键词: RI; Small; Understanding; Inductive; Bias

Deep neural networks have had a huge recent impact on the world. They are widely used in systems that understand speech, translate language, and analyze images. In spite of their great impact, researchers still lack a rigorous understanding of many of the basic properties of these networks. As a consequence, new networks are largely designed laboriously, through trial and error. And although extremely effective overall, these systems are sometimes fooled by examples that seem very simple, and similar to other examples that are easily handled. This research aims to provide a better theoretical understanding of an important class of neural networks, called Convolutional Neural Networks (CNNs), which are widely used in understanding images and audio signals. The project focuses on understanding what problems will be easy or difficult for CNNs. This understanding can help us to predict biases in these networks and understand how the design of a network will affect its behavior. The project will provide research opportunities for graduate, undergraduate and high school students, particularly reaching out to students from underrepresented groups.Two key properties that distinguish CNNs from many other approaches to machine learning are their ability to naturally incorporate multiscale analysis and invariance or equivariance. This property has enabled the construction of shift invariant networks that effectively deal with images and signals sampled on grid data, and more recently of networks that handle sets and graphs, incorporating operations that are equivariant to set permutation and graph isomorphism. Multiscale representations naturally arise in these networks through their depth. This research focuses on gaining a better understanding of the role of multiscale, invariance and equivariance in neural networks. It will study how shift invariance and multiscale representations affect the dynamics of neural network training. Our approach will build on recent results showing that massively overparameterized neural networks can be represented as kernel methods. Analyzing the properties of these kernels will help us understand the relationship between a network's architecture and its inductive biases. The insights revealed have the potential to provide a more principled way to control these biases.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

深度神经网络最近对世界产生了巨大的影响。它们广泛应用于理解语音、翻译语言和分析图像的系统中。尽管影响巨大，但研究人员仍然对这些网络的许多基本特性缺乏严格的理解。因此，新网络很大程度上是通过反复试验而费力设计的。尽管总体上非常有效，但这些系统有时会被看似非常简单且与其他易于处理的示例类似的示例所愚弄。这项研究旨在为一类重要的神经网络（称为卷积神经网络（CNN））提供更好的理论理解，该网络广泛用于理解图像和音频信号。该项目的重点是了解哪些问题对于 CNN 来说是容易的或困难的。这种理解可以帮助我们预测这些网络中的偏差，并了解网络的设计将如何影响其行为。该项目将为研究生、本科生和高中生提供研究机会，特别是为来自代表性不足群体的学生提供研究机会。CNN 与许多其他机器学习方法的区别的两个关键特性是它们自然地结合多尺度分析和不变性或等变性的能力。这一特性使得能够构建有效处理网格数据上采样的图像和信号的平移不变网络，以及最近处理集合和图的网络，合并与集合排列和图同构等变的操作。多尺度表示通过其深度自然地出现在这些网络中。这项研究的重点是更好地理解神经网络中多尺度、不变性和等变性的作用。它将研究平移不变性和多尺度表示如何影响神经网络训练的动态。我们的方法将建立在最近的结果之上，该结果表明大规模过度参数化的神经网络可以表示为核方法。分析这些内核的属性将帮助我们理解网络架构与其归纳偏差之间的关系。所揭示的见解有可能提供一种更有原则的方法来控制这些偏见。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentation

• DOI: 10.1109/iccv51070.2023.00384
• 发表时间: 2023-03
• 期刊: 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
• 作者: K. Pnvr;Bharat Singh;P. Ghosh;Behjat Siddiquie;David Jacobs

HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions

• DOI: 10.1109/cvpr52729.2023.01807
• 发表时间: 2023-04
• 期刊: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Anshul B. Shah;A. Roy;Ketul Shah;Shlok Kumar Mishra;David W. Jacobs;A. Cherian;Ramalingam Chellappa

Hyperbolic Contrastive Learning for Visual Representations beyond Objects

• DOI: 10.1109/cvpr52729.2023.00661
• 发表时间: 2022-12
• 期刊: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Songwei Ge;Shlok Kumar Mishra;Simon Kornblith;Chun-Liang Li;David Jacobs

Autoregressive Perturbations for Data Poisoning

• DOI: 10.48550/arxiv.2206.03693
• 发表时间: 2022-06
• 期刊: ArXiv
• 作者: Pedro Sandoval-Segura;Vasu Singla;Jonas Geiping;Micah Goldblum;T. Goldstein;David Jacobs

Measured Albedo in the Wild: Filling the Gap in Intrinsics Evaluation

• DOI: 10.1109/iccp56744.2023.10233761
• 发表时间: 2023-06
• 期刊: 2023 IEEE International Conference on Computational Photography (ICCP)
• 作者: Jiaye Wu;Sanjoy Chowdhury;Hariharmano Shanmugaraja;David Jacobs;Soumyadip Sengupta