Mattdl/ContinualEvaluation

[Spotlight ICLR 2023 paper] Continual evaluation for lifelong learning with neural networks, identifying the stability gap.

34
/ 100
Emerging

When developing or deploying AI models that learn continuously over time, it's crucial to understand how well they retain old knowledge while learning new tasks. This tool helps machine learning engineers and researchers assess the real-time performance of their lifelong learning models, providing fine-grained insights into how accuracy changes at every learning step. It takes in your model and training data, and outputs detailed performance metrics that highlight potential drops in stability.

No commits in the last 6 months.

Use this if you are developing AI systems that learn continually and need a more rigorous way to evaluate their performance stability, especially for safety-critical applications.

Not ideal if you are working with traditional machine learning models that are trained once and then deployed without continuous updates.

lifelong-learning continual-learning machine-learning-evaluation model-robustness AI-safety
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

35

Forks

4

Language

Python

License

MIT

Last pushed

Apr 02, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Mattdl/ContinualEvaluation"

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