matlab-deep-learning/neuron-coverage-for-deep-learning

Compute the neuron coverage of a deep learning network in MATLAB.

21
/ 100
Experimental

This tool helps deep learning practitioners and researchers assess the effectiveness of their test data for neural networks. You provide a trained deep learning network and a set of test data in MATLAB, and it calculates which parts (neurons) of the network are activated by that data. The output tells you how much of your network is 'covered' by your tests, helping you understand if your tests are thorough.

No commits in the last 6 months.

Use this if you are a deep learning engineer or researcher using MATLAB and want to measure how much of your neural network is 'exercised' by your existing test datasets to identify potential blind spots.

Not ideal if you are not working with deep learning models, do not use MATLAB, or are looking for a tool to generate new test cases automatically rather than evaluate existing ones.

deep-learning neural-networks model-testing machine-learning-quality-assurance AI-testing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

10

Forks

Language

MATLAB

License

Last pushed

Oct 04, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/matlab-deep-learning/neuron-coverage-for-deep-learning"

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