arXiv Computation and Language By Zhuoya Zhao, Parsa Omidi, Aref Jafari, Richard Naud

Large Language Models with At Most One Spike per Neuron

Read the original on arXiv Computation and Language →

The paper presents a spiking neural network (SNN) approach that uses time-to-first-spike (TTFS) coding to limit each neuron to at most one spike per time window, enabling energy-efficient large language models (LLMs). A reference-based strategy is introduced to encode the four core LLM components—embedding layers, layer normalization, attention-related operations, and dropout—allowing the construction of a fully TTFS-based SNN architecture trained end-to-end. Experiments on BERT and GPT-2 show performance comparable to artificial neural network (ANN) counterparts on natural language understanding and common-sense reasoning, while achieving a 1.5‑billion‑parameter spiking LLM and providing an estimate of spike-related energy consumption.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI
Aug 11

SuperNeuroMAT: An Efficient Matrix-based Simulator for Spiking Neural Networks

arXiv:2608. 08479v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) offer a promising pathway to energy-efficient AI and brain-inspired computing.

By Prasanna Date, Kevin Zhu, Shruti Kulkarni, Ashish Gautam, Chathika Gunaratne, Robert Patton, Tyler Nitzsche, Ian Mulet, Zachary Johnson-Scott, Addison Helms, Duncan Rowden, Simon Weston, Maryam Parsa, Catherine Schuman, Thomas Potok