DOE OSTI · 2947333
Artificial to Spiking Neural Networks Conversion with Calibration in Scientific Machine Learning
Abstract
Here, we introduce a method to convert physics-informed neural networks (PINNs), commonly used in scientific machine learning, to spiking neural networks (SNNs), which are expected to have higher energy efficiency compared to traditional artificial neural networks (ANNs). We first extend the calibration technique of SNNs to arbitrary activation functions beyond ReLU, making it more versatile, and we prove a theorem that ensures the effectiveness of the calibration. We successfully convert PINNs to SNNs, enabling computational efficiency for diverse regression tasks in solving multiple differential equations, including the unsteady Navier–Stokes equations. We demonstrate great gains in terms of overall efficiency, including separable PINNs (SPINNs), which accelerate the training process. Overall, this is the first work of this kind and the proposed method achieves relatively good accuracy with low spike rates.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Zhang, Qian [Brown Univ., Providence, RI (United States)] (ORCID:0000000246520699), Wu, Chenxi [Brown Univ., Providence, RI (United States)] (ORCID:000000026099126X), Kahana, Adar [Brown Univ., Providence, RI (United States)] (ORCID:0000000348895037), Karniadakis, George Em [Brown Univ., Providence, RI (United States)] (ORCID:0000000297137120), Kim, Youngeun [Yale Univ., New Haven, CT (United States)], Li, Yuhang [Yale Univ., New Haven, CT (United States)], Panda, Priyadarshini [Yale Univ., New Haven, CT (United States)]. 2025-05-02. Artificial to Spiking Neural Networks Conversion with Calibration in Scientific Machine Learning. https://doi.org/10.1137/24m1643232
Cite the original work for its findings. Save a collection to share your selection of sources.