Producing Explainable AI (XAI) and Interpretable Machine Learning Solutions
Source: Frank Kane
Learn why the need for XAI has been rapidly increasing in recent years. Explore available methods and common techniques for XAI and IML, as well as when and how to use each. Keith walks you through the challenges and opportunities of black box models, showing you how to bring transparency to your models and using real-world examples that illustrate tricks of the trade on the easy-to-learn, open-source KNIME Analytics Platform. By the end of this course, you’ll have a better understanding of XAI and IML techniques for both global and local explanations.
Explicit vs Implicit
Explicit
- Things you like, share, review, or dislike.
- Data can be too sparse as additional work needed by user to provide data and not all will provide explicit feedbacks.
- Different standard, meaning of a 4 star review might be different between 2 people.
Implicit
- Things you click on, purchase or consume
- A lot of data but can be noisy data, due to misclick or bots
- But purchase data can help reduced that, however there are techniques such as brushing
Top-N recommender
Candidate generation . Filtering . Ranking
Focus on limited quantity of resource