Benchmarking and survey of explanation methods for black box models
Total time needed: ~3 hours
The widespread adoption of black-box models in Artificial Intelligence has enhanced the need for explanation methods to reveal how these obscure models reach specific decisions. Retrieving explanations is fundamental to unveil possible biases and to resolve practical or ethical issues. Nowadays, the literature is full of methods with different explanations. We provide a categorization of explanation methods based on the type of explanation returned. We present the most recent and widely used explainers, and we show a visual comparison among explanations and a quantitative benchmarking.
Potential Use Cases
Explainable AI Survey
Who is This For ?
INTERMEDIATEMachine learning practitioners
Click on each of the following annotated items to see details.
ARTICLE 1. Benchmarking and survey of explanation methods for black box models
What are the different approaches of Explainable AI?
How we can categorize different approaches?
What are the different evaluation metrics for Explainable AI?
What are the available tools for Explainable AI?
VIDEO 2. A discussion on Explainable AI methods for black box models
What are the different approaches and tools for Explainable AI?
ARTICLE 3. What are the tools for Explainable AI?
What are the different tools for Explainable AI?
ARTICLE 4. What is the taxonomy of Explainable AI approaches?
What are the different categories of the Explainable AI methods?
ARTICLE 5. What are the evaluation measures for Explainable AI?
What are the evaluation approaches for Explainable AI?