torchsde
pysindy
| torchsde | pysindy | |
|---|---|---|
| 5 | 5 | |
| 1,473 | 1,293 | |
| 2.0% | 2.8% | |
| 4.8 | 9.3 | |
| 7 months ago | 7 days ago | |
| Python | Python | |
| Apache License 2.0 | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
torchsde
-
Google Research • Differentiable SDE solvers with GPU support and efficient sensitivity analysis in PyTorch. For stochastic differential equations in your deep learning models
Github: https://github.com/google-research/torchsde
-
[D] Ideal deep learning library
So not just that paper, but also our follow-up papers on the same topic: Neural SDEs as Infinite-Dimensional GANs Efficient and Accurate Gradients for Neural SDEs are in fact implemented in PyTorch, specifically the torchsde library. (Disclaimer: of which I am a developer.)
-
[D] Is there any way for GAN to generate arbitrary length of time series signal?
Code: SDE-GAN example in torchsde.
-
[P] Final Year Computer Science Project Suggestions
If you're interested in finance then I'd recommend Neural SDEs: https://arxiv.org/abs/2102.03657 https://arxiv.org/abs/2105.13493 https://github.com/google-research/torchsde/blob/master/examples/sde_gan.py
-
Simple & Fast GAN Training [D]
This may or may not fit what you're after.
pysindy
- Sam Altman's ouster was precipitated by letter to board about AI breakthrough
-
Ask HN: Why don't datacenters have passive rooflines like Net Zero homes?
https://github.com/dynamicslab/pysindy/issues/383#event-1002...
awesome-machine-learning-fluid-mechanics >
- Why are neural networks not multi-dimensional?
- Creating an equation for a system given its data.
-
Physics-Based Deep Learning Book
Not MLP, but PySindy[0] might be a way to find a closed form solution. A simple MLP may not be best way to achieve what are you are after.
[0] https://github.com/dynamicslab/pysindy
What are some alternatives?
torchdyn - A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods
sysidentpy - A Python Package For System Identification Using NARMAX Models
tabnet - PyTorch implementation of TabNet paper : https://arxiv.org/pdf/1908.07442.pdf
Poincare-Maps - MATLAB files for discovery of Poincaré maps
SSD-pytorch - SSD: Single Shot MultiBox Detector pytorch implementation focusing on simplicity
thebe - Turn static HTML pages into live documents with Jupyter kernels.
NeuralCDE - Code for "Neural Controlled Differential Equations for Irregular Time Series" (Neurips 2020 Spotlight)
pbdl-book - Welcome to the Physics-based Deep Learning Book (v0.2)
functorch - functorch is JAX-like composable function transforms for PyTorch.
diffrax - Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
pix2pixHD - Synthesizing and manipulating 2048x1024 images with conditional GANs
Stochastic-Processes - My book: Gentle Introduction to Chaotic Dynamical Systems. Includes stochastic dynamical systems and statistical properties of numeration systems in any dimension.