# Grid cells and their potential application in AI

arXiv: https://arxiv.org/abs/2210.12068 · HTML: https://mlsanity.com/paper/2210.12068/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 34 references that are in the map.
- First posted on arXiv 12 Oct 2022.

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

- [Relating transformers to models and neural representations of the hippocampal formation](https://mlsanity.com/paper/2112.04035/) (2021)
- [Grid Cell Path Integration For Movement-Based Visual Object Recognition](https://mlsanity.com/paper/2102.09076/) (2021)

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

- [Metacognition is all you need? Using Introspection in Generative Agents to Improve Goal-directed Behavior](https://mlsanity.com/paper/2401.10910/) (2024)

## Abstract (arXiv)

Since their Nobel Prize winning discovery in 2005, grid cells have been studied extensively by neuroscientists. Their multi-scale periodic firing rates tiling the environment as the animal moves around has been shown as critical for path integration. Multiple experiments have shown that grid cells also fire for other representations such as olfactory, attention mechanisms, imagined movement, and concept organization potentially acting as a form of neural recycling and showing the possible brain mechanism for cognitive maps that Tolman envisioned in 1948. Grid cell integration into artificial neural networks may enable more robust, generalized, and smarter computers. In this paper we give an overview of grid cell research since their discovery, their role in neuroscience and cognitive science, and possible future directions of artificial intelligence research.