20026-08-20 パシフィック・ノースウェスト国立研究所（PNNL）
New research highlights how spiking neural networks can be effective for the regression tasks key to scientific machine learning. (Image by Stephanie King | Pacific Northwest National Laboratory)
＜関連情報＞
- https://www.pnnl.gov/publications/improving-prediction-ability-spiking-neural-networks
- https://www.nature.com/articles/s44387-026-00121-2
LIFからQIFへ：科学的機械学習のための微分可能なスパイクニューロンに向けて From LIF to QIF: Toward differentiable spiking neurons for scientific machine learning
Ruyin Wan,George Em Karniadakis & Panos Stinis
npj Artificial Intelligence Published:27 June 2026
DOI:https://doi.org/10.1038/s44387-026-00121-2 Early provide
Abstract
Spiking neural networks (SNNs) offer biologically inspired computation but remain underexplored for continuous regression tasks in scientific machine learning. In this work, we introduce and systematically evaluate Quadratic Integrate-and-Fire (QIF) neurons as an alternative to the conventional Leaky Integrate-and-Fire (LIF) model in both directly trained SNNs and ANN-to-SNN conversion frameworks. The QIF neuron exhibits smooth and differentiable spiking dynamics, enabling gradient-based training and stable optimization within architectures such as multilayer perceptrons (MLPs), Deep Operator Networks (DeepONets), and Physics-Informed Neural Networks (PINNs). Across benchmarks on function approximation, operator learning, and partial differential equation (PDE) solving, QIF-based networks yield smoother, more accurate, and more stable predictions than their LIF counterparts, which suffer from discontinuous time-step responses and jagged activation surfaces. These results position the QIF neuron as a computational bridge between spiking and continuous-valued deep learning, advancing the integration of neuroscience-inspired dynamics into physics-informed and operator-learning frameworks.
