arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.12424cs.LGcs.AI
收藏

人工神经网络中的可解释模型

Interpretable Models in ANNs

University of Victoria(维多利亚大学)

Yang Li

摘要:

人工神经网络通常非常复杂,并且对于人类来说太深而无法理解。因此,它们通常被称为黑匣子。对于许多现实世界的问题,底层模式本身非常复杂,因此不存在分析解决方案。但是,在某些情况下,物理定律,例如,图案可以用相对简单的数学表达式来描述。在这种情况下,我们希望得到一个可读的方程,而不是一个黑盒子。在本文中,我们试图找到一种解释网络的方法,并提取一个描述模型的人类可读方程。

英文摘要:

Artificial neural networks are often very complex and too deep for a human to understand. As a result, they are usually referred to as black boxes. For a lot of real-world problems, the underlying pattern itself is very complicated, such that an analytic solution does not exist. However, in some cases, laws of physics, for example, the pattern can be described by relatively simple mathematical expressions. In that case, we want to get a readable equation rather than a black box. In this paper, we try to find a way to explain a network and extract a human-readable equation that describes the model.

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。

↑