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 2005.10691cs.LGcs.AIstat.ML
收藏

通过基于约束的领域知识改进深度学习模型:简要综述

Improving Deep Learning Models via Constraint-Based Domain Knowledge: a Brief Survey

University of Bologna(博洛尼亚大学)

Andrea Borghesi, Federico Baldo, Michela Milano

摘要:

事实证明,深度学习(DL)模型在各种各样的学习任务中表现非常出色,因为它们可以从大型数据集中学习有用的模式。然而,当需要学习非常困难的函数或没有足够的可用训练数据时,纯数据驱动的模型可能会遇到困难。幸运的是,在许多领域,先验信息可以被检索并用于提高DL模型的性能。本文提出了第一次调查的方法,旨在整合领域知识,表示的形式的约束,在DL学习模型,以提高其性能,特别是针对深度神经网络。我们确定了五个(非互斥的)类别,包括注入领域知识的主要方法:1)作用于特征空间,2)修改假设空间,3)数据增强,4)正则化方案,5)约束学习。

英文摘要:

Deep Learning (DL) models proved themselves to perform extremely well on a wide variety of learning tasks, as they can learn useful patterns from large data sets. However, purely data-driven models might struggle when very difficult functions need to be learned or when there is not enough available training data. Fortunately, in many domains prior information can be retrieved and used to boost the performance of DL models. This paper presents a first survey of the approaches devised to integrate domain knowledge, expressed in the form of constraints, in DL learning models to improve their performance, in particular targeting deep neural networks. We identify five (non-mutually exclusive) categories that encompass the main approaches to inject domain knowledge: 1) acting on the features space, 2) modifications to the hypothesis space, 3) data augmentation, 4) regularization schemes, 5) constrained learning.

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。

↑