google-deepmind/learning-to-learn

Learning to Learn in TensorFlow

48
/ 100
Emerging

This project helps machine learning engineers improve the training process of neural networks and other models. It takes a machine learning problem (like image classification or a quadratic function) and outputs a custom-trained optimizer. This optimizer can then be used to more efficiently train other models, potentially achieving better performance or faster convergence than standard optimizers.

4,071 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or practitioner looking to develop novel optimization strategies for training your models more effectively.

Not ideal if you are looking for an off-the-shelf solution for model training and prefer to use standard, well-established optimizers without custom development.

deep-learning-research model-optimization neural-network-training algorithm-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

4,071

Forks

602

Language

Python

License

Apache-2.0

Last pushed

Jun 29, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/google-deepmind/learning-to-learn"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.