paper-with-me

홈 › Papers

Scalable Mechanistic Neural Networks for Differential Equations and Machine Learning

2024-10-08 · Jiale Chen, Dingling Yao, Adeel Pervez, Dan Alistarh, Francesco Locatello

We propose Scalable Mechanistic Neural Network (S-MNN), an enhanced neural network framework designed for scientific machine learning applications involving long temporal sequences. By reformulating the original Mechanistic Neural Network (MNN) (Pervez et al., 2024), we reduce the computational time and space complexities from cubic and quadratic with respect to the sequence length, respectively, to linear. This significant improvement enables efficient modeling of long-term dynamics without sacrificing accuracy or interpretability. Extensive experiments demonstrate that S-MNN matches the original MNN in precision while substantially reducing computational resources. Consequently, S-MNN can drop-in replace the original MNN in applications, providing a practical and efficient tool for integrating mechanistic bottlenecks into neural network models of complex dynamical systems. Source code is available at https://github.com/IST-DASLab/ScalableMNN.

📄 PDF Abstract BibTeX arXiv:2410.06074

Code (1)

IST-DASLab/ScalableMNN 공식 구현 pytorch

Tasks

Temporal Sequences

Similar Papers 제목 키워드 기반

Mechanistic Neural Networks for Scientific Machine Learning

2024-02-20 · Adeel Pervez, Francesco Locatello, Efstratios Gavves

This paper presents Mechanistic Neural Networks, a neural network design for machine learning applications in the sciences. It incorporates a new Mechanistic Block in standard architectures to explicitly learn governing …

Equation DiscoveryGPU

Mechanistic PDE Networks for Discovery of Governing Equations

2025-02-25 · Adeel Pervez, Efstratios Gavves, Francesco Locatello

We present Mechanistic PDE Networks -- a model for discovery of governing partial differential equations from data. Mechanistic PDE Networks represent spatiotemporal data as space-time dependent linear partial differenti…

GPU

Assessment of Uncertainty Quantification in Universal Differential Equations

2024-06-13 · Nina Schmid, David Fernandes del Pozo, Willem Waegeman, Jan Hasenauer

Scientific Machine Learning is a new class of approaches that integrate physical knowledge and mechanistic models with data-driven techniques for uncovering governing equations of complex processes. Among the available a…

Uncertainty QuantificationVariational Inference

EARS-UDE: Evaluating Auditory Response in Sensory Overload with Universal Differential Equations

2025-10-16 · Miheer Salunke, Prathamesh Dinesh Joshi, Raj Abhijit Dandekar, Rajat Dandekar 외 arxiv

Auditory sensory overload affects 50-70% of individuals with Autism Spectrum Disorder (ASD), yet existing approaches, such as mechanistic models (Hodgkin Huxley type, Wilson Cowan, excitation inhibition balance), clinica…

Graph Neural Ordinary Differential Equations for Coarse-Grained Socioeconomic Dynamics

2024-07-25 · James Koch, Pranab Roy Chowdhury, Heng Wan, Parin Bhaduri 외

We present a data-driven machine-learning approach for modeling space-time socioeconomic dynamics. Through coarse-graining fine-scale observations, our modeling framework simplifies these complex systems to a set of trac…

Sensitivity