Saved in:
| Main Authors: | , , , , , |
|---|---|
| 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 |