leveraging aisara algorithm for effective hyperparameter tuning
Project description
aisaratuners is a hyperparameter tuning library that can be used with different machine learning and deep learning python packages. It leverages AiSara algorithm, Latin hypercube sampling, and the concept of search space reduction for fast reach of the optimum hyperparameters combination.
- Currently available for Keras, scikit-learn and PyTorch will be added in the coming versions
AiSara Hyperparameter Tuning API
AiSara Artificial Intelligence
Change Log
1.4.5 (19/11/2020)
- First Release
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
aisaratuners-1.4.5.tar.gz
(10.0 kB
view hashes)
Built Distribution
Close
Hashes for aisaratuners-1.4.5-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 30bec4b2b7a0e090cb68b82914fef4e263ab2e0b36399df784036f48bf1d5406 |
|
MD5 | f276b9085b1adbf6c9f5674b39887f77 |
|
BLAKE2b-256 | 20a62f9995640bb8a4470d934e44886c3b3b748bc476c22c539150ee93182677 |