forgi86/lru-reduction
Python code of the paper Model order reduction of deep structured state-space models: A system-theoretic approach
This project helps control engineers and system modelers simplify complex dynamic models of systems like aircraft or chemical processes. It takes a detailed, high-order 'Linear Recurrent Unit' (LRU) model, often used in deep learning, and reduces it to a much simpler, lower-order version. The output is a more efficient, but equally effective, model that's easier to analyze and simulate. This is for professionals working with system identification and control.
No commits in the last 6 months.
Use this if you need to reduce the complexity of high-dimensional state-space models to make them more manageable for analysis and simulation without losing essential system behavior.
Not ideal if you are working with static datasets or machine learning models that do not rely on a time-variant state-space representation.
Stars
14
Forks
1
Language
Python
License
MIT
Category
Last pushed
Nov 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/forgi86/lru-reduction"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
kaanaksit/odak
Scientific computing library for optics, computer graphics and visual perception.
NVIDIA/torch-harmonics
Differentiable signal processing on the sphere for PyTorch
PreFab-Photonics/PreFab
Artificial nanofabrication of integrated photonic circuits using deep learning
MatthewFilipovich/torchoptics
Differentiable wave optics simulation library built on PyTorch
artificial-scientist-lab/XLuminA
XLuminA, a highly-efficient, auto-differentiating discovery framework for super-resolution microscopy.