# Discretization of continuous input spaces in the hippocampal autoencoder

arXiv: https://arxiv.org/abs/2405.14600 · HTML: https://mlsanity.com/paper/2405.14600/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 58 references that are in the map.
- First posted on arXiv 23 May 2024.

## Builds on (most cited first, 6 of 6)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [On 1/n neural representation and robustness](https://mlsanity.com/paper/2012.04729/) (2020)
- [The Animal-AI Environment: Training and Testing Animal-Like Artificial Cognition](https://mlsanity.com/paper/1909.07483/) (2019)
- [Interneurons accelerate learning dynamics in recurrent neural networks for statistical adaptation](https://mlsanity.com/paper/2209.10634/) (2022)
- [Adaptive whitening with fast gain modulation and slow synaptic plasticity](https://mlsanity.com/paper/2308.13633/) (2023)

## Built on by (most cited first, 1 of 1)

- [High-fidelity social learning via shared episodic memories enhances collaborative foraging through mnemonic convergence](https://mlsanity.com/paper/2412.20271/) (2024)

## Abstract (arXiv)

The hippocampus has been associated with both spatial cognition and episodic memory formation, but integrating these functions into a unified framework remains challenging. Here, we demonstrate that forming discrete memories of visual events in sparse autoencoder neurons can produce spatial tuning similar to hippocampal place cells. We then show that the resulting very high-dimensional code enables neurons to discretize and tile the underlying image space with minimal overlap. Additionally, we extend our results to the auditory domain, showing that neurons similarly tile the frequency space in an experience-dependent manner. Lastly, we show that reinforcement learning agents can effectively perform various visuo-spatial cognitive tasks using these sparse, very high-dimensional representations.