A robust package for extrapolation control in neural networks
Project description
XtrapNet
XtrapNet is a robust package for extrapolation control in neural networks. It provides advanced uncertainty quantification, ensemble methods, and fallback mechanisms to improve predictions in out-of-distribution regions.
Installation
pip install xtrapnet
Usage
from xtrapnet import XtrapNet, XtrapTrainer, XtrapController
net = XtrapNet(input_dim=2) trainer = XtrapTrainer(net, num_epochs=100) trainer.train(labels, features) xtrap_ctrl = XtrapController(trained_model=net, train_features=features, train_labels=labels, mode='clip')
predictions = xtrap_ctrl.predict([[0.5, 0.5]]) print(predictions) License MIT License
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file xtrapnet-0.1.0.tar.gz.
File metadata
- Download URL: xtrapnet-0.1.0.tar.gz
- Upload date:
- Size: 1.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c1ab3479e6065510022085b7e07bf79f2d8e802330ade551b961f0524f278175
|
|
| MD5 |
8ffb61046f2ad6ba4e784f7ab3a09a03
|
|
| BLAKE2b-256 |
5b1175833706a9c9056e7e92e171061dc5ca9a611aa7776774da8699719f4f50
|
File details
Details for the file xtrapnet-0.1.0-py3-none-any.whl.
File metadata
- Download URL: xtrapnet-0.1.0-py3-none-any.whl
- Upload date:
- Size: 1.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e9c97f8362405cba4da290562df62eadfabf9190d5d3eb2d5987612520ccacaf
|
|
| MD5 |
2e091067a50d0703a9c583bdf65cd85c
|
|
| BLAKE2b-256 |
194ace1854ef805c4db73b35bde4a959e9b33b0f95eabf6a80f2f60a2b775ac2
|
