samholt/NeuralLaplace
Neural Laplace: Differentiable Laplace Reconstructions for modelling any time observation with O(1) complexity.
This library helps machine learning engineers and researchers model complex real-world systems described by differential equations, especially when dealing with observations that occur at irregular times. It takes a mathematical description of a system in the Laplace domain and reconstructs how that system changes over time. Researchers working with continuous-time models in deep learning will find this useful for handling time-series data with varying observation intervals.
No commits in the last 6 months.
Use this if you need to build machine learning models that interpret and predict the behavior of systems described by differential equations, especially when your data arrives at irregular time intervals.
Not ideal if you are looking for a simple, off-the-shelf solution for basic time-series forecasting without needing to delve into differential equations or Laplace transforms.
Stars
82
Forks
12
Language
Python
License
MIT
Category
Last pushed
Apr 19, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/samholt/NeuralLaplace"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lululxvi/deepxde
A library for scientific machine learning and physics-informed learning
pnnl/neuromancer
Pytorch-based framework for solving parametric constrained optimization problems,...
wilsonrljr/sysidentpy
A Python Package For System Identification Using NARMAX Models
dynamicslab/pysindy
A package for the sparse identification of nonlinear dynamical systems from data
google-research/torchsde
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.