arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1312.4209cs.LG
收藏

特征图架构

Feature Graph Architectures

University of Sydney(悉尼大学)

Richard Davis, Sanjay Chawla, Philip Leong

摘要:

在这篇文章中,我们提出了特征图架构(FGA),这是一种深度学习系统,采用基于特征图的结构化初始化和训练方法,与标准浅层架构相比,该方法有助于提高泛化性能。我们的目标是探索深度网络训练问题的替代观点。我们在一些实验数据集上评估了深度SVM的FGA性能,并展示了这些模型的泛化和稳定性结果。我们描述了置换对模型精度的影响,并根据特征相关性给出了最佳置换的判据。实验结果表明,该算法产生了强大的和显着的测试集的改进,一个标准的浅SVM训练方法的范围内的数据集。这些增益是在时间复杂度适度增加的情况下实现的。

英文摘要:

In this article we propose feature graph architectures (FGA), which are deep learning systems employing a structured initialisation and training method based on a feature graph which facilitates improved generalisation performance compared with a standard shallow architecture. The goal is to explore alternative perspectives on the problem of deep network training. We evaluate FGA performance for deep SVMs on some experimental datasets, and show how generalisation and stability results may be derived for these models. We describe the effect of permutations on the model accuracy, and give a criterion for the optimal permutation in terms of feature correlations. The experimental results show that the algorithm produces robust and significant test set improvements over a standard shallow SVM training method for a range of datasets. These gains are achieved with a moderate increase in time complexity.

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。

↑