# The structure of evolved representations across different substrates for artificial intelligence

arXiv: https://arxiv.org/abs/1804.01660 · HTML: https://mlsanity.com/paper/1804.01660/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Apr 2018.

## Built on by (most cited first, 2 of 2)

- [Detecting Information Relays in Deep Neural Networks](https://mlsanity.com/paper/2301.00911/) (2023)
- [Identifying Information-Transfer Nodes in a Recurrent Neural Network Reveals Dynamic Representations](https://mlsanity.com/paper/2510.01271/) (2025)

## Abstract (arXiv)

Artificial neural networks (ANNs), while exceptionally useful for classification, are vulnerable to misdirection. Small amounts of noise can significantly affect their ability to correctly complete a task. Instead of generalizing concepts, ANNs seem to focus on surface statistical regularities in a given task. Here we compare how recurrent artificial neural networks, long short-term memory units, and Markov Brains sense and remember their environments. We show that information in Markov Brains is localized and sparsely distributed, while the other neural network substrates "smear" information about the environment across all nodes, which makes them vulnerable to noise.