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 2211.06137cs.LG
收藏

DNN 中概念的涌现?

Emergence of Concepts in DNNs?

University of Bern(伯尔尼大学)

Tim Räz

AI总结:

本文结合哲学视角批判性综述 DNN 隐藏层概念识别方法,分析预测准确性与压缩对概念空间的塑造,并指出人类识别 DNN 所表示概念的能力仍严重受限。

摘要:

本文回顾并讨论了计算机科学中提出的、旨在识别 DNN 内部表示(隐藏层)中概念的工作。首先,文章考察了现有方法究竟如何识别据称在 DNN 中得到表示的概念。其次,讨论了概念空间——即内部表示中的概念集合——如何由预测准确性与压缩之间的权衡所塑造。文章借助哲学对这些问题进行了批判性审视。尽管有证据表明 DNN 能够表示概念之间非平凡的推理关系,但我们识别概念的能力受到严重限制。

英文摘要:

The present paper reviews and discusses work from computer science that proposes to identify concepts in internal representations (hidden layers) of DNNs. It is examined, first, how existing methods actually identify concepts that are supposedly represented in DNNs. Second, it is discussed how conceptual spaces -- sets of concepts in internal representations -- are shaped by a tradeoff between predictive accuracy and compression. These issues are critically examined by drawing on philosophy. While there is evidence that DNNs able to represent non-trivial inferential relations between concepts, our ability to identify concepts is severely limited.

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。

↑