Starting Sep. 5, 2020, active development of nnitp is moving to https://github.com/kenmcmil/nnitp
Nnitp is a tool for interpretability of neural network inferences using Bayesian interpolants. The basic technique is described in this paper. It currently supports convolutional neural networks for image classification, using the Keras framework.
Documentation on nnitp can be found here
This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.
When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.
This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.