mit-mseas/neuralClosureModels
Code for the framework, neural closure models.
This project helps researchers and scientists improve predictions for complex dynamical systems by learning how to account for neglected details in simplified models. It takes data from high-fidelity simulations to produce 'neural closure models' that enhance the accuracy of predictions from faster, lower-fidelity models. This is ideal for scientists, engineers, and researchers working with physical, biological, or environmental simulations where computational cost is a barrier to using full-complexity models.
No commits in the last 6 months.
Use this if you need to make accurate long-term predictions from simplified or coarse models of complex systems, and you have access to data from high-fidelity simulations.
Not ideal if you do not work with dynamical systems, do not have high-fidelity simulation data, or are not concerned with the computational efficiency of your models.
Stars
8
Forks
2
Language
Jupyter Notebook
License
—
Category
Last pushed
May 29, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mit-mseas/neuralClosureModels"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
keras-team/keras
Deep Learning for humans
Lightning-AI/torchmetrics
Machine learning metrics for distributed, scalable PyTorch applications.
Lightning-AI/pytorch-lightning
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
lanpa/tensorboardX
tensorboard for pytorch (and chainer, mxnet, numpy, ...)