Oscillator-Based Associative Memory with Exponential Capacity: Theory, Algorithms, and Hardware Implementation

• URL: http://arxiv.org/abs/2604.01469v1
• Date: Wed, 01 Apr 2026 23:26:10 GMT
• Title: Oscillator-Based Associative Memory with Exponential Capacity: Theory, Algorithms, and Hardware Implementation
• Abstract summary: Associative memory systems enable content-addressable storage and retrieval of patterns.<n>We present an associative memory architecture based on Kuramoto oscillator networks with honeycomb topology.<n>We prove that this architecture achieves exponential memory capacity.
• Score: 4.337876197068824
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Exponential Capacity in Multilayer Hetero-Associative Neural Networks [1.5749416770494706]
  We study an exponential neural network of $L$ layers of $N$ binary neurons.<n>We find that the exponential capacity and the predicted basins survive correlated, many-to-one patterns.
  arXiv  Detail & Related papers  (2026-07-31T15:46:21Z)
• Factual recall in linear associative memories: sharp asymptotics and mechanistic insights [11.11958822145404]
  We study the limits of storing and retrieving input--output associations with neural networks.<n>A linear associative memory maps $p$ input embeddings in $mathbbRd$ to their corresponding$d$-dimensional targets.<n>We show that a decoupled model can store up to $p_c log p_c / d2 = 1 / 2$ associations.
  arXiv  Detail & Related papers  (2026-05-11T16:24:02Z)
• Higher-Order Kuramoto Oscillator Network for Dense Associative Memory [0.0]
  We show that higher-order couplings achieve superlinear scaling of memory capacity with system size.<n>These results bridge the Kuramoto synchronization with modern Hopfield memories.
  arXiv  Detail & Related papers  (2025-07-29T16:35:52Z)
• Latent Structured Hopfield Network for Semantic Association and Retrieval [52.634915010996835]
  Episodic memory enables humans to recall past experiences by associating semantic elements such as objects, locations, and time into coherent event representations.<n>We propose the Latent Structured Hopfield Network (LSHN), a framework that integrates continuous Hopfield attractor dynamics into an autoencoder architecture.<n>Unlike traditional Hopfield networks, our model is trained end-to-end with gradient descent, achieving scalable and robust memory retrieval.
  arXiv  Detail & Related papers  (2025-06-02T04:24:36Z)
• B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory [91.81390121042192]
  We develop a class of models called B'MOJO to seamlessly combine eidetic and fading memory within an composable module. B'MOJO's ability to modulate eidetic and fading memory results in better inference on longer sequences tested up to 32K tokens.
  arXiv  Detail & Related papers  (2024-07-08T18:41:01Z)
• Topology-aware Embedding Memory for Continual Learning on Expanding Networks [63.35819388164267]
  We present a framework to tackle the memory explosion problem using memory replay techniques. PDGNNs with Topology-aware Embedding Memory (TEM) significantly outperform state-of-the-art techniques.
  arXiv  Detail & Related papers  (2024-01-24T03:03:17Z)
• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• Kernel Memory Networks: A Unifying Framework for Memory Modeling [9.142894972380216]
  We consider the problem of training a neural network to store a set of patterns with maximal noise robustness. A solution is derived by training each individual neuron to perform either kernel classification or with a minimum weight norm. We derive optimal models, termed kernel memory networks, that include, as special cases, many of the hetero- and auto-associative memory models.
  arXiv  Detail & Related papers  (2022-08-19T16:01:09Z)
• Quantum associative memory with a single driven-dissipative nonlinear oscillator [0.0]
  We propose a realization of associative memory with a single driven-dissipative quantum oscillator. The model can improve the storage capacity of discrete neuron-based systems in a large regime. We show that the associative-memory capacity is inherently related to the existence of a spectral gap in the Liouvillian superoperator.
  arXiv  Detail & Related papers  (2022-05-19T12:00:35Z)
• Cross-Frequency Coupling Increases Memory Capacity in Oscillatory Neural Networks [69.42260428921436]
  Cross-frequency coupling (CFC) is associated with information integration across populations of neurons. We construct a model of CFC which predicts a computational role for observed $theta - gamma$ oscillatory circuits in the hippocampus and cortex. We show that the presence of CFC increases the memory capacity of a population of neurons connected by plastic synapses.
  arXiv  Detail & Related papers  (2022-04-05T17:13:36Z)
• High-Capacity Expert Binary Networks [56.87581500474093]
  Network binarization is a promising hardware-aware direction for creating efficient deep models. Despite its memory and computational advantages, reducing the accuracy gap between binary models and their real-valued counterparts remains an unsolved challenging research problem. We propose Expert Binary Convolution, which, for the first time, tailors conditional computing to binary networks by learning to select one data-specific expert binary filter at a time conditioned on input features.
  arXiv  Detail & Related papers  (2020-10-07T17:58:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.