Business Analytics and Emerging Trends - Responsible AI - Explainable AI
6 important questions on Business Analytics and Emerging Trends - Responsible AI - Explainable AI
What is exaplainable AI?
Why is exaplainable AI important?
- Trustworthiness
- Fairness
- Privacy awareness
- Transferability
What are two XAI directions?
- Glassbox models: make model transparent from start
- Blackbox explainers: make non-transparent models and explain output by extra means
- Higher grades + faster learning
- Never study anything twice
- 100% sure, 100% understanding
In what ways can post-hoc explainabilities of blackbox models occur?
- Text explanations
- Visual explanations
- Explanations by example
- Explanations by simplifications
For what types of AI methods are glass boxes (transparent machine models) useful?
- ML methods
- Decision trees (simulatable and decomposable and have high transparency)
- Random forest (can attain higher generalizability, less overfitting)
- Rule based learners
What is LIME in explainable AI?
The question on the page originate from the summary of the following study material:
- A unique study and practice tool
- Never study anything twice again
- Get the grades you hope for
- 100% sure, 100% understanding