R.I.P.
๐ป
Ghosted
Hyperbolic Neural Population Geometry Benefits Computation
June 08, 2026 ยท Grace Period ยท ๐ ICML 2026
Authors
Dennis Wu, Yi-Chun Hung, Braden Yuille, James E. Fitzgerald, Han Liu
arXiv ID
2606.10238
Category
q-bio.NC
Cross-listed
cs.AI
Citations
0
Venue
ICML 2026
Abstract
Neural population geometry shapes downstream computation. Recent empirical findings in neurobiology suggest that a hyperbolic structure underlies population activity in the hippocampus. Here we provide a theoretical framework for this phenomenon. First, we propose a plausible construction of hippocampal tuning curves that statistically induces hyperbolic geometry. Next, we establish a connection between neural decoding and associative memory by demonstrating that the Modern Hopfield Network update rule computes the minimum mean-squared-error (MMSE) estimator. Finally, we introduce a novel associative memory model defined in hyperbolic space that yields significantly larger capacity than leading models. Our results suggest that animals encode spatial information as a latent hyperbolic cognitive map, improving both memory capacity and decoding accuracy.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ q-bio.NC
R.I.P.
๐ป
Ghosted
SuperSpike: Supervised learning in multi-layer spiking neural networks
R.I.P.
๐ป
Ghosted
Generic decoding of seen and imagined objects using hierarchical visual features
R.I.P.
๐ป
Ghosted
Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future
R.I.P.
๐ป
Ghosted
A probabilistic atlas of the human thalamic nuclei combining ex vivo MRI and histology
R.I.P.
๐ป
Ghosted