Wave-Based Semantic Memory with Resonance-Based Retrieval: A Phase-Aware Alternative to Vector Embedding Stores
- URL: http://arxiv.org/abs/2509.09691v1
- Date: Thu, 21 Aug 2025 10:13:24 GMT
- Title: Wave-Based Semantic Memory with Resonance-Based Retrieval: A Phase-Aware Alternative to Vector Embedding Stores
- Authors: Aleksandr Listopad,
- Abstract summary: We propose a novel framework that models knowledge as wave patterns $psi(x) = A(x) eiphi(x)$ and retrieves it through resonance-based interference.<n>This approach preserves both amplitude and phase information, enabling more expressive and robust semantic similarity.
- Score: 51.56484100374058
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Conventional vector-based memory systems rely on cosine or inner product similarity within real-valued embedding spaces. While computationally efficient, such approaches are inherently phase-insensitive and limited in their ability to capture resonance phenomena crucial for meaning representation. We propose Wave-Based Semantic Memory, a novel framework that models knowledge as wave patterns $\psi(x) = A(x) e^{i\phi(x)}$ and retrieves it through resonance-based interference. This approach preserves both amplitude and phase information, enabling more expressive and robust semantic similarity. We demonstrate that resonance-based retrieval achieves higher discriminative power in cases where vector methods fail, including phase shifts, negations, and compositional queries. Our implementation, ResonanceDB, shows scalability to millions of patterns with millisecond latency, positioning wave-based memory as a viable alternative to vector stores for AGI-oriented reasoning and knowledge representation.
Related papers
- Latent-Mark: An Audio Watermark Robust to Neural Resynthesis [62.09761127079914]
Latent-Mark is the first zero-bit audio watermarking framework designed to survive semantic compression.<n>Our key insight is that robustness to the encode-decode process requires embedding the watermark within the invariant latent space.<n>Our work inspires future research into universal watermarking frameworks capable of maintaining integrity across increasingly complex and diverse generative distortions.
arXiv Detail & Related papers (2026-03-05T15:51:09Z) - SYNAPSE: Empowering LLM Agents with Episodic-Semantic Memory via Spreading Activation [29.545442480332515]
We introduce Synapse, a unified memory architecture that transcends static rather than pre-computed links.<n>We show that Synapse significantly outperforms state-of-the-art methods in complex temporal and multi-hop reasoning tasks.<n>Our code and data will be made publicly available upon acceptance.
arXiv Detail & Related papers (2026-01-06T06:19:58Z) - Phase-Coded Memory and Morphological Resonance: A Next-Generation Retrieval-Augmented Generator Architecture [0.0]
Instead of token embeddings, the system encodes meaning as complex wave patterns with amplitude-phase structure.<n>The paper outlines theoretical foundations, pseudocode implementation, and experimental evidence from related complex-valued neural models.
arXiv Detail & Related papers (2025-11-14T20:12:24Z) - Scalable Distributed Memory Implementation of the Quasi-Adiabatic Propagator Path Integral [0.0]
We present a scalable distributed memory implementation of the Mask Assisted Coarse Graining of Influence Coefficients.<n>The method exploits the memory resources of multiple compute nodes and mitigates the memory bottleneck via a new pre-merging algorithm.<n>The efficiency of the new implementation is demonstrated in large-scale dissipative quantum dynamics simulations.
arXiv Detail & Related papers (2025-06-03T17:56:18Z) - SigWavNet: Learning Multiresolution Signal Wavelet Network for Speech Emotion Recognition [17.568724398229232]
Speech emotion recognition (SER) plays an important role in emotional states from deciphering speech signals.<n>This paper introduces a new end-to-end (E2E) deep learning multi-resolution framework for SER.<n>It exploits the capabilities of wavelets for effective localization in both time and frequency domains.
arXiv Detail & Related papers (2025-02-01T04:18:06Z) - The Backpropagation of the Wave Network [26.656105779121308]
This paper provides an in-depth analysis of Wave Network, a novel token representation method derived from the Wave Network.<n>In complex vector token representation, each token is represented with a magnitude component, capturing the global semantics of the entire input text.<n>A detailed computational complexity analysis shows that Token2Wave can significantly reduce video memory usage and training time.
arXiv Detail & Related papers (2024-11-11T13:48:01Z) - Point-Based Value Iteration for POMDPs with Neural Perception Mechanisms [31.51588071503617]
We introduce neuro-symbolic partially observable Markov decision processes (NS-POMDPs)
We propose a novel piecewise linear and convex representation (P-PWLC) in terms of polyhedra covering the state space and value vectors.
We show the practical applicability of our approach on two case studies that employ (trained) ReLU neural networks as perception functions.
arXiv Detail & Related papers (2023-06-30T13:26:08Z) - On the Relationship Between Variational Inference and Auto-Associative
Memory [68.8204255655161]
We study how different neural network approaches to variational inference can be applied in this framework.
We evaluate the obtained algorithms on the CIFAR10 and CLEVR image datasets and compare them with other associative memory models.
arXiv Detail & Related papers (2022-10-14T14:18:47Z) - Universal Face Restoration With Memorized Modulation [73.34750780570909]
This paper proposes a Restoration with Memorized Modulation (RMM) framework for universal Blind Face Restoration (BFR)
We apply random noise as well as unsupervised wavelet memory to adaptively modulate the face-enhancement generator.
Experimental results show the superiority of the proposed method compared with the state-of-the-art methods, and a good generalization in the wild.
arXiv Detail & Related papers (2021-10-03T15:55:07Z) - Particle Track Classification Using Quantum Associative Memory [0.3058685580689604]
Pattern recognition algorithms are commonly employed to simplify the step of track reconstruction in sub-atomic physics experiments.
We study quantum associative memory based on quantum annealing and apply it to the particle track classification.
We characterize classification performance of these approaches as a function detector resolution, pattern library size, and detector inefficiencies, using the D-Wave 2000Q processor as a testbed.
arXiv Detail & Related papers (2020-11-24T02:32:19Z) - Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence
Modeling [61.351967629600594]
This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq), non-parallel voice conversion approach.
In this approach, we combine a bottle-neck feature extractor (BNE) with a seq2seq synthesis module.
Objective and subjective evaluations show that the proposed any-to-many approach has superior voice conversion performance in terms of both naturalness and speaker similarity.
arXiv Detail & Related papers (2020-09-06T13:01:06Z) - Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating
Back-Propagation for Saliency Detection [54.98042023365694]
We propose a noise-aware encoder-decoder framework to disentangle a clean saliency predictor from noisy training examples.
The proposed model consists of two sub-models parameterized by neural networks.
arXiv Detail & Related papers (2020-07-23T18:47:36Z) - MetaSDF: Meta-learning Signed Distance Functions [85.81290552559817]
Generalizing across shapes with neural implicit representations amounts to learning priors over the respective function space.
We formalize learning of a shape space as a meta-learning problem and leverage gradient-based meta-learning algorithms to solve this task.
arXiv Detail & Related papers (2020-06-17T05:14:53Z)
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.