LioNets v2
A Neural-Specific Local Interpretation Technique Exploiting Penultimate Layer Information
Explainable AI (XAI) is recently treated as a huge step towards reliable systems, enhancing the trust of people to AI. Interpretable machine learning (IML), a subfield of XAI, is also an urgent topic of research. This component, named LioNets, presents a small but significant contribution to the IML community, focusing on a local-based, neural-specific interpretation process applied to textual and time-series data.
Hardware architecture: X64
Install and Run: Please ensure you have docker installed on your desktop. Download the component. Then run in your terminal
>>> docker build -t lionets .
After successfully installing LioNets, please do:
>>> docker run -p 8888:8888 lionets .
Then, in your terminal copy the localhost url and open it in your browser. Enjoy :)
Additional information: The proposed methodology introduces new approaches to the presentation of feature importance based interpretations, as well as the production of counterfactual words on textual datasets. Eventually, an improved evaluation metric is introduced for the assessment of interpretation techniques, which supports an extensive set of qualitative and quantitative experiments.
This component is the second version of the previous component called LioNets.