论文标题
DNN中的概念的出现？
Emergence of Concepts in DNNs?
论文作者
论文摘要
本文审查并讨论了计算机科学的工作，该作品建议在DNN的内部表示（隐藏层）中识别概念。首先，对现有方法进行了研究，如何实际识别DNN中所代表的概念。其次，讨论了概念空间（内部表示中的概念集）如何取决于预测精度和压缩之间的权衡。这些问题通过利用哲学进行了严格的研究。尽管有证据表明DNN能够代表概念之间的非平凡推论关系，但我们识别概念的能力受到严重限制。
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.
