arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1504.08022cs.LGcs.NE
收藏

一种高阶交互结构化输出的深度学习模型

A Deep Learning Model for Structured Outputs with High-order Interaction

National Research Council of Canada(加拿大国家研究委员会);NEC Labs America(NEC美国实验室)

Hongyu Guo, Xiaodan Zhu, Martin Renqiang Min

摘要:

许多现实世界的应用程序都与结构化数据相关联,其中不仅输入而且输出都有相互作用。然而,典型的分类和回归模型往往缺乏同时探索输入和输出中高阶交互作用的能力。在本文中,我们提出了一个深度学习模型,旨在生成从结构化输入到结构化输出的强大的非线性函数映射。更具体地说,我们建议整合高阶隐藏单元,指导判别式预训练和高阶自动编码器。我们用三个数据集对模型进行了评估,并在竞争性方法中获得了最先进的性能。我们目前的工作重点是结构化输出回归,这是一个较少探索的领域,尽管该模型可以扩展到处理结构化标签分类。

英文摘要:

Many real-world applications are associated with structured data, where not only input but also output has interplay. However, typical classification and regression models often lack the ability of simultaneously exploring high-order interaction within input and that within output. In this paper, we present a deep learning model aiming to generate a powerful nonlinear functional mapping from structured input to structured output. More specifically, we propose to integrate high-order hidden units, guided discriminative pretraining, and high-order auto-encoders for this purpose. We evaluate the model with three datasets, and obtain state-of-the-art performances among competitive methods. Our current work focuses on structured output regression, which is a less explored area, although the model can be extended to handle structured label classification.

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。

↑