arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1805.11204cs.LGstat.ML
收藏

对称正定矩阵流形上的统计回归模型

A Statistical Recurrent Model on the Manifold of Symmetric Positive Definite Matrices

University of Florida(佛罗里达大学);University of Wisconsin Madison(威斯康星大学麦迪逊分校)

Rudrasis Chakraborty, Chun-Hao Yang, Xingjian Zhen, Monami Banerjee, Derek Archer, David Vaillancourt, Vikas Singh, Baba C. Vemuri

摘要:

在许多学科中,数据(例如,图、流形)在本质上是非欧几里得的。几何深度学习对应于将深度神经网络模型推广到这种非欧几里德空间的技术。最近的几篇论文已经展示了如何将卷积神经网络(CNN)扩展到使用基于图形的数据进行学习。在这项工作中,我们研究了数据(或测量)在本质上是有序的,纵向的或时间的,并且生活在黎曼流形上的设置-这种设置在统计机器学习,视觉和医学成像中的各种问题中很常见。我们展示了如何经常性的统计经常性网络模型可以定义在这样的空间。我们给出了一个有效的算法,并对其统计特性进行了严格的分析。我们进行了大量的数值实验,证明竞争力的性能与最先进的方法,但与显着较少的参数。我们还展示了在脑成像中的统计分析任务的应用,这是一个深度神经网络模型仅以有限的方式被利用的领域。

英文摘要:

In a number of disciplines, the data (e.g., graphs, manifolds) to be analyzed are non-Euclidean in nature. Geometric deep learning corresponds to techniques that generalize deep neural network models to such non-Euclidean spaces. Several recent papers have shown how convolutional neural networks (CNNs) can be extended to learn with graph-based data. In this work, we study the setting where the data (or measurements) are ordered, longitudinal or temporal in nature and live on a Riemannian manifold -- this setting is common in a variety of problems in statistical machine learning, vision and medical imaging. We show how recurrent statistical recurrent network models can be defined in such spaces. We give an efficient algorithm and conduct a rigorous analysis of its statistical properties. We perform extensive numerical experiments demonstrating competitive performance with state of the art methods but with significantly less number of parameters. We also show applications to a statistical analysis task in brain imaging, a regime where deep neural network models have only been utilized in limited ways.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑