tensorflow/adanet
Fast and flexible AutoML with learning guarantees.
This framework helps machine learning practitioners build high-quality predictive models for tasks like classification or regression without extensive manual tuning. You provide your raw data and define some potential model components, and the system automatically combines them into an optimized ensemble. Data scientists, ML engineers, and researchers can use this to quickly develop powerful models.
3,457 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to rapidly develop and deploy accurate machine learning models and want to automate the complex process of finding the best neural network architectures and combining multiple models.
Not ideal if you require complete manual control over every layer and parameter of your neural network architecture, or if you are not working with TensorFlow.
Stars
3,457
Forks
527
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Nov 30, 2023
Commits (30d)
0
Dependencies
8
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tensorflow/adanet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
optuna/optuna
A hyperparameter optimization framework
keras-team/keras-tuner
A Hyperparameter Tuning Library for Keras
KernelTuner/kernel_tuner
Kernel Tuner
syne-tune/syne-tune
Large scale and asynchronous Hyperparameter and Architecture Optimization at your fingertips.
deephyper/deephyper
DeepHyper: A Python Package for Massively Parallel Hyperparameter Optimization in Machine Learning