Extensional Properties of Recurrent Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914997830942720 |
|---|---|
| author | Dantsin, Evgeny Wolpert, Alexander |
| author_facet | Dantsin, Evgeny Wolpert, Alexander |
| contents | A property of a recurrent neural network (RNN) is called \emph{extensional} if, loosely speaking, it is a property of the function computed by the RNN rather than a property of the RNN algorithm. Many properties of interest in RNNs are extensional, for example, robustness against small changes of input or good clustering of inputs. Given an RNN, it is natural to ask whether it has such a property. We give a negative answer to the general question about testing extensional properties of RNNs. Namely, we prove a version of Rice's theorem for RNNs: any nontrivial extensional property of RNNs is undecidable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_22730 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Extensional Properties of Recurrent Neural Networks Dantsin, Evgeny Wolpert, Alexander Neural and Evolutionary Computing Machine Learning A property of a recurrent neural network (RNN) is called \emph{extensional} if, loosely speaking, it is a property of the function computed by the RNN rather than a property of the RNN algorithm. Many properties of interest in RNNs are extensional, for example, robustness against small changes of input or good clustering of inputs. Given an RNN, it is natural to ask whether it has such a property. We give a negative answer to the general question about testing extensional properties of RNNs. Namely, we prove a version of Rice's theorem for RNNs: any nontrivial extensional property of RNNs is undecidable. |
| title | Extensional Properties of Recurrent Neural Networks |
| topic | Neural and Evolutionary Computing Machine Learning |
| url | https://arxiv.org/abs/2410.22730 |