This is the official code library for:
"Explaining Deep Learning using examples: Optimal feature weighting methods for twin systems using post-hoc, explanation-by-example in XAI": Published at Knowledge-Based Systems: Link here.
A PyTorch library available via "pip install" will be made available as soon as possible.
This work is an extension of the conference paper published at IJCAI 2019 here.
Firstly, and explanation-by-example method will be available in the first version of the library.
Next, we will introduce the added ability to highlight key features used in the classification, and from where they arose in the training data.
We appreciate your patience, it should all be finished relatively soon.
If you need something sooner, there is a manual example of how to use twin-systems with C-HP feature-weighting (the best kind) here.