Papers › Discretization of continuous input spaces in the hippocampal autoencoder

Discretization of continuous input spaces in the hippocampal autoencoder

23 May 2024arXiv:2405.14600archive 2025-07-28

Adrian F. Amil, Ismael T. Freire, Paul F. M. J. Verschure

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.

PaperPDFCode

Code

adriamilcar/hashingbrain officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Sparse Autoencoder

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections