# Extensional Properties of Recurrent Neural Networks

arXiv: https://arxiv.org/abs/2410.22730 · HTML: https://mlsanity.com/paper/2410.22730/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 23 references that are in the map.
- First posted on arXiv 30 Oct 2024.

## Builds on (most cited first, 2 of 2)

- [NLP Verification: Towards a General Methodology for Certifying Robustness](https://mlsanity.com/paper/2403.10144/) (2024)
- [Reinforcement Learning Neural Turing Machines - Revised](https://mlsanity.com/paper/1505.00521/) (2015)

## Abstract (arXiv)

A property of a recurrent neural network (RNN) is called 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.