https://github.com/vu-luong/onn-tensorflow
Tensorflow implementation of the Online Deep Learning: Learning Deep Neural Networks on the Fly paper.
https://github.com/vu-luong/onn-tensorflow
online-deep-learning online-learning tensorflow
Last synced: 2 months ago
JSON representation
Tensorflow implementation of the Online Deep Learning: Learning Deep Neural Networks on the Fly paper.
- Host: GitHub
- URL: https://github.com/vu-luong/onn-tensorflow
- Owner: vu-luong
- Created: 2019-12-10T01:46:53.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2021-06-11T02:13:17.000Z (over 4 years ago)
- Last Synced: 2025-04-08T17:12:43.896Z (6 months ago)
- Topics: online-deep-learning, online-learning, tensorflow
- Language: Python
- Homepage:
- Size: 49.8 KB
- Stars: 4
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Online Neural Network (ONN)
This is a Tensorflow implementation of the [Online Deep Learning: Learning Deep Neural Networks on the Fly](https://arxiv.org/abs/1711.03705) paper.
## Installing
```
```
## How to use
```python
from benchmark.onn import ONN
model = ONN(n_features, n_classes, n_layers=n_layers, learning_rate=learning_rate)
# Make prediction
pred = model.predict(inputs)
# Update model
model.partial_fit(inputs, targets)
```
* See the file `main.py` for prequential evaluation of ONN+ADWIN
## References
- [Online Deep Learning: Learning Deep Neural Networks on the Fly](https://arxiv.org/abs/1711.03705)