arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.11152stat.MLcs.LGcs.NE
收藏

关于人工神经网络非线性的基本问题

Fundamental Issues Regarding Uncertainties in Artificial Neural Networks

University of Manchester(曼彻斯特大学);University of Sheffield(谢菲尔德大学);Goethe-Universität(歌德大学)

Neil A. Thacker, Carole J. Twining, Paul D. Tar, Scott Notley, Visvanathan Ramesh

摘要:

人工神经网络(ANN)实现了一种特定形式的多变量外推,并将为任何输入模式生成输出,即使没有类似的训练模式。外推不一定是可信的,为了支持安全关键系统,我们要求这些系统给出与其输出相关的训练样本相关不确定性的指示。有些读者可能认为这是一个众所周知的问题,已经被模式识别的基本原理所涵盖。我们将在下面解释为什么情况并非如此,以及分类的常规条件概率(的李克复估计)如何不能正确评估这种不确定性。我们提供了一个讨论这个问题的标准解释,并显示如何定量的方法,长期以来的方法的基础上,可以实际应用。该方法说明了使用磁共振成像的痴呆症的早期诊断的任务。

英文摘要:

Artificial Neural Networks (ANNs) implement a specific form of multi-variate extrapolation and will generate an output for any input pattern, even when there is no similar training pattern. Extrapolations are not necessarily to be trusted, and in order to support safety critical systems, we require such systems to give an indication of the training sample related uncertainty associated with their output. Some readers may think that this is a well known issue which is already covered by the basic principles of pattern recognition. We will explain below how this is not the case and how the conventional (Likelihood estimate of) conditional probability of classification does not correctly assess this uncertainty. We provide a discussion of the standard interpretations of this problem and show how a quantitative approach based upon long standing methods can be practically applied. The methods are illustrated on the task of early diagnosis of dementing diseases using Magnetic Resonance Imaging.

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。

↑