Saved in:
Bibliographic Details
Main Authors: Kalra, Archit, Sadanand, Midhun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.07361
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915485980819456
author Kalra, Archit
Sadanand, Midhun
author_facet Kalra, Archit
Sadanand, Midhun
contents Spiking neural networks offer a promising path toward energy-efficient, brain-like associative memory. This paper introduces Word2Spike, a novel rate coding mechanism that combines continuous word embeddings and neuromorphic architectures. We develop a one-to-one mapping that converts multi-dimensional word vectors into spike-based attractor states using Poisson processes. Using BitNet b1.58 quantization, we maintain 97% semantic similarity of continuous embeddings on SimLex-999 while achieving 100% reconstruction accuracy on 10,000 words from OpenAI's text-embedding-3-large. We preserve analogy performance (100% of original embedding performance) even under intentionally introduced noise, indicating a resilient mechanism for semantic encoding in neuromorphic systems. Next steps include integrating the mapping with spiking transformers and liquid state machines (resembling Hopfield Networks) for further evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2509_07361
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Word2Spike: Poisson Rate Coding for Associative Memories and Neuromorphic Algorithms
Kalra, Archit
Sadanand, Midhun
Neural and Evolutionary Computing
Artificial Intelligence
Spiking neural networks offer a promising path toward energy-efficient, brain-like associative memory. This paper introduces Word2Spike, a novel rate coding mechanism that combines continuous word embeddings and neuromorphic architectures. We develop a one-to-one mapping that converts multi-dimensional word vectors into spike-based attractor states using Poisson processes. Using BitNet b1.58 quantization, we maintain 97% semantic similarity of continuous embeddings on SimLex-999 while achieving 100% reconstruction accuracy on 10,000 words from OpenAI's text-embedding-3-large. We preserve analogy performance (100% of original embedding performance) even under intentionally introduced noise, indicating a resilient mechanism for semantic encoding in neuromorphic systems. Next steps include integrating the mapping with spiking transformers and liquid state machines (resembling Hopfield Networks) for further evaluation.
title Word2Spike: Poisson Rate Coding for Associative Memories and Neuromorphic Algorithms
topic Neural and Evolutionary Computing
Artificial Intelligence
url https://arxiv.org/abs/2509.07361