Country
You are in the Nigeria edition. Type your country to switch.
Nigeria
Loading every country…
No country matches. Check the spelling, or choose "Any country" for the Global edition.
Your learning profile
AI ethics and responsible AI · Lesson 3 of 9
Transparency and explainability
People deserve to know when AI is involved in something that affects them, and to get an explanation they can understand. This lesson covers disclosure, plain-language explanations, documentation such as model cards, and the honest limits of explaining complex models.
This lesson is complete in writing. A video for it is on its way.
What you will learn
- By the end you can explain what AI transparency means for affected people, users and overseers.
- You can tell weak disclosure from good disclosure and write a clear notice.
- You can improve a decision explanation so it gives real reasons and a route to challenge.
- You can describe what a model card covers and why the limits of explanation matter.
Key terms in this lesson
- AI transparency
- Being open about when and how AI is used, what it does, what data it relies on and what its limits are, so that affected people can understand and question it.
- Explainability
- How well people can understand why a model produced a given output, in terms of which inputs mattered and in which direction.
- Deepfake
- A video, image or audio clip made or altered with AI so a real person appears to say or do something they never did.
- EU AI Act
- The European Union's law on artificial intelligence, which sorts AI uses into risk tiers and places the heaviest duties on uses it treats as high risk, such as credit scoring of individuals.
- Model card
- A short document that records what a model is for, the data it learned from, how it was tested, where it performs poorly, who owns it and when it was last reviewed.
- Step 1: What transparency means, not started
- Step 2: Telling people when AI is involved, not started
- Step 3: Explaining a decision in plain words, not started
- Step 4: Model cards and documentation, not started
- Step 5: The limits of explanation, not started
About 10 min of reading
Step 1 of 5
What transparency means
Opening this step…
Step 2 of 5
Telling people when AI is involved
This step opens when you finish the one above.
Step 3 of 5
Explaining a decision in plain words
This step opens when you finish the one above.
Step 4 of 5
Model cards and documentation
This step opens when you finish the one above.
Step 5 of 5
The limits of explanation
This step opens when you finish the one above.
Key takeaways
The key takeaways open when you finish every step.
Lesson quiz
5 questions. You need 85% to pass.
The quiz opens when you finish every step.
Read first
Stockertim Learn is education. It explains how investing works and never recommends buying or selling anything.
Popular this week: Basics: BeginnerNGX & Africa: Beginner