Word2Spike: Poisson Rate Coding for Associative Memories and Neuromorphic Algorithms
This addresses the challenge of semantic encoding for energy-efficient neuromorphic computing, though it appears incremental as it builds on existing word embeddings and quantization techniques.
The paper tackles the problem of converting continuous word embeddings into spike-based representations for neuromorphic associative memory systems, achieving 97% semantic similarity on SimLex-999 and 100% reconstruction accuracy on 10,000 words while maintaining full analogy performance under noise.
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.