# Implementing engrams from a machine learning perspective: the relevance of a latent space

arXiv: https://arxiv.org/abs/2407.16616 · HTML: https://mlsanity.com/paper/2407.16616/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 3 references that are in the map.
- First posted on arXiv 23 Jul 2024.

## Builds on (most cited first, 1 of 1)

- [LTC-SE: Expanding the Potential of Liquid Time-Constant Neural Networks for Scalable AI and Embedded Systems](https://mlsanity.com/paper/2304.08691/) (2023)

## Abstract (arXiv)

In our previous work, we proposed that engrams in the brain could be biologically implemented as autoencoders over recurrent neural networks. These autoencoders would comprise basic excitatory/inhibitory motifs, with credit assignment deriving from a simple homeostatic criterion. This brief note examines the relevance of the latent space in these autoencoders. We consider the relationship between the dimensionality of these autoencoders and the complexity of the information being encoded. We discuss how observed differences between species in their connectome could be linked to their cognitive capacities. Finally, we link this analysis with a basic but often overlooked fact: human cognition is likely limited by our own brain structure. However, this limitation does not apply to machine learning systems, and we should be aware of the need to learn how to exploit this augmented vision of the nature.