{"ID":2872855,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.07361","arxiv_id":"2509.07361","title":"Word2Spike: Poisson Rate Coding for Associative Memories and Neuromorphic Algorithms","abstract":"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.","short_abstract":"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 int...","url_abs":"https://arxiv.org/abs/2509.07361","url_pdf":"https://arxiv.org/pdf/2509.07361v1","authors":"[\"Archit Kalra\",\"Midhun Sadanand\"]","published":"2025-09-09T03:15:22Z","proceeding":"cs.NE","tasks":"[\"cs.NE\",\"cs.AI\"]","methods":"[\"Transformer\"]","has_code":false}