leopard-ai/betty

Betty: an automatic differentiation library for generalized meta-learning and multilevel optimization

40
/ 100
Emerging

This is a specialized tool for machine learning researchers and practitioners who are building advanced AI models. It helps streamline the process of developing complex multi-level optimization problems, such as fine-tuning hyperparameters, optimizing neural network architectures, or improving data sampling strategies. You provide definitions for different interdependent optimization tasks, and the tool manages the complex interactions and gradient calculations to produce more performant and robust AI models.

346 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or advanced practitioner working with complex models that require simultaneous optimization of multiple, interdependent components, like those found in meta-learning or hyperparameter optimization.

Not ideal if you are new to machine learning, only need to train simple models, or are looking for a high-level API for standard supervised learning tasks.

meta-learning hyperparameter-optimization neural-architecture-search data-reweighting machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

346

Forks

29

Language

Python

License

Apache-2.0

Last pushed

Jun 26, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/leopard-ai/betty"

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