Explainable AI Framework Comparisio
Explainable AI (XAI) refers to methods and techniques in the application of artificial intelligence (AI) such that the reason of the solution/prediction can be understood by humans. It contrasts with the concept of the "black box" in machine learning where even their designers cannot explain why the AI arrived at a specific decision. It is the extent to which the internal mechanics of a machine or deep learning system can be explained in human terms. It is important to understand the difference between interpreting a model and explaining “why” a system behaves the way it does.
In the notebooks in this repository, we have used three different dataset:
- Bank Churner Dataset
- Apple Disease Detection
- Helmet Detection On the above dataset, models have been trained extensively and on top of that XAI frameworks have been applied for justifying the prediction made by model. The explainations are analysed using several rules and calculations and explainations are made more justifiable for the instance.