Saved in:
Bibliographic Details
Main Authors: Ogranovich, Arie, Guo, Taosha, Venkatakrishnan, Arvind R., Shapiro, Madelyn, Bullo, Francesco, Pasqualetti, Fabio
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.01469
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910096638869504
author Ogranovich, Arie
Guo, Taosha
Venkatakrishnan, Arvind R.
Shapiro, Madelyn
Bullo, Francesco
Pasqualetti, Fabio
author_facet Ogranovich, Arie
Guo, Taosha
Venkatakrishnan, Arvind R.
Shapiro, Madelyn
Bullo, Francesco
Pasqualetti, Fabio
contents Associative memory systems enable content-addressable storage and retrieval of patterns, a capability central to biological neural computation and artificial intelligence. Classical implementations such as Hopfield networks face fundamental limitations in memory capacity, scaling at most linearly with network size. We present an associative memory architecture based on Kuramoto oscillator networks with honeycomb topology in which memories are encoded as stable phase-locked configurations. The honeycomb network consists of multiple cycles that share nodes in a chain-like arrangement, creating a one-dimensional lattice of chained+loops. We prove that this architecture achieves exponential memory capacity: a network of $N$ oscillators can store $(2\lceil n_c/4 \rceil - 1)^m$ distinct patterns, where $m$ honeycomb cycles each contain $n_c$ oscillators. Moreover, we fully characterize all stable configurations and prove that each memory's basin of attraction maintains a guaranteed minimum size independent of network scale. Simulations using charge-density-wave (CDW) oscillators validate predicted phase-locking behavior, demonstrating practical realizability in neuromorphic hardware.
format Preprint
id arxiv_https___arxiv_org_abs_2604_01469
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Oscillator-Based Associative Memory with Exponential Capacity: Theory, Algorithms, and Hardware Implementation
Ogranovich, Arie
Guo, Taosha
Venkatakrishnan, Arvind R.
Shapiro, Madelyn
Bullo, Francesco
Pasqualetti, Fabio
Neural and Evolutionary Computing
Associative memory systems enable content-addressable storage and retrieval of patterns, a capability central to biological neural computation and artificial intelligence. Classical implementations such as Hopfield networks face fundamental limitations in memory capacity, scaling at most linearly with network size. We present an associative memory architecture based on Kuramoto oscillator networks with honeycomb topology in which memories are encoded as stable phase-locked configurations. The honeycomb network consists of multiple cycles that share nodes in a chain-like arrangement, creating a one-dimensional lattice of chained+loops. We prove that this architecture achieves exponential memory capacity: a network of $N$ oscillators can store $(2\lceil n_c/4 \rceil - 1)^m$ distinct patterns, where $m$ honeycomb cycles each contain $n_c$ oscillators. Moreover, we fully characterize all stable configurations and prove that each memory's basin of attraction maintains a guaranteed minimum size independent of network scale. Simulations using charge-density-wave (CDW) oscillators validate predicted phase-locking behavior, demonstrating practical realizability in neuromorphic hardware.
title Oscillator-Based Associative Memory with Exponential Capacity: Theory, Algorithms, and Hardware Implementation
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2604.01469