arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1710.09302stat.MLcs.LG
收藏

深度神经网络

Deep Neural Networks

Rice University(莱斯大学)

Randall Balestriero, Richard Baraniuk

摘要:

深度神经网络(DNN)是通用函数逼近器,为广泛的应用提供最先进的解决方案。常见的感知任务,如语音识别,图像分类和对象跟踪,现在通常通过DNN处理。一些基本问题仍然存在:(1)缺乏为任何拓扑提供明确和可解释的输入输出公式的数学框架,(2)关于对抗性示例的DNN稳定性的量化(即,修改后的输入欺骗了DNN预测,同时人类无法检测到),(3)缺乏泛化保证和模糊模式的可控行为,(4)利用未标记的数据将DNN应用于专家标记稀缺的领域,如医学领域。将这些观点结合起来,将为在共同基础上的进一步发展提供理论视角。此外,DNN现在被部署在巨大的社会应用中,推动了填补这一理论空白的需求,以确保控制,可靠性和可解释性。

英文摘要:

Deep Neural Networks (DNNs) are universal function approximators providing state-of- the-art solutions on wide range of applications. Common perceptual tasks such as speech recognition, image classification, and object tracking are now commonly tackled via DNNs. Some fundamental problems remain: (1) the lack of a mathematical framework providing an explicit and interpretable input-output formula for any topology, (2) quantification of DNNs stability regarding adversarial examples (i.e. modified inputs fooling DNN predictions whilst undetectable to humans), (3) absence of generalization guarantees and controllable behaviors for ambiguous patterns, (4) leverage unlabeled data to apply DNNs to domains where expert labeling is scarce as in the medical field. Answering those points would provide theoretical perspectives for further developments based on a common ground. Furthermore, DNNs are now deployed in tremendous societal applications, pushing the need to fill this theoretical gap to ensure control, reliability, and interpretability.

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。

↑