mlsanityData to 14 Oct 2026

Word2Spike: Poisson Rate Coding for Associative Memories and Neuromorphic Algorithms

arXiv 2509.07361 ↗First posted 9 Sep 2025cs.NE cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 26 references that are in the map. First posted on arXiv 9 Sep 2025.

Builds on

15 of 26 references.

References · 15

  1. 2024The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bitscited by 308
  2. 2022Spikformer: When Spiking Neural Network Meets Transformercited by 271
  3. 2016Dense Associative Memory for Pattern Recognitioncited by 236
  4. 2022Liquid Structural State-Space Modelscited by 136
  5. 2023SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networkscited by 88
  6. 2022Rate Coding or Direct Coding: Which One is Better for Accurate, Robust, and Energy-efficient Spiking Neural Networks?cited by 25
  7. 2023Exploiting Noise as a Resource for Computation and Learning in Spiking Neural Networkscited by 18
  8. 2023SpikeBERT: A Language Spikformer Learned from BERT with Knowledge Distillationcited by 17
  9. 2025Episodic Memories Generation and Evaluation Benchmark for Large Language Modelscited by 14
  10. 2018Near-lossless Binarization of Word Embeddingscited by 13
  11. 2021Noise-Robust Deep Spiking Neural Networks with Temporal Informationcited by 5
  12. 2019Reinforcement Learning with Low-Complexity Liquid State Machinescited by 4
3 more
  1. 2020Faster Binary Embeddings for Preserving Euclidean Distancescited by 4
  2. 2024Spiking representation learning for associative memoriescited by 3
  3. 2024Stochastic Spiking Neural Networks with First-to-Spike Codingcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Rethinking the Tradeoff Between Temporal Encoding and Nonlinear Computation in Spiking Language Models
  2. 2025Memory-Free and Parallel Computation for Quantized Spiking Neural Networks
  3. 2025A PyTorch-Compatible Spike Encoding Framework for Energy-Efficient Neuromorphic Applications
  4. 2024Exploring Extreme Quantization in Spiking Language Models
  5. 2023SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiation
  6. 2026Modern Neuromorphic AI: From Intra-Token to Inter-Token Processing
  7. 2026Determinism in the Undetermined: Deterministic Output in Charge-Conserving Continuous-Time Neuromorphic Systems with Temporal Stochasticity
  8. 2025All in one timestep: Enhancing Sparsity and Energy efficiency in Multi-level Spiking Neural Networks