Bài Quiz không có tiêu đề

Which of the following is an explainability risk of self-learning models?

• Self-learning models are unable to generate decisions as output.
• Self-learning models may introduce new data you're unaware of.
• Self-learning models are black boxes whose decisions cannot be understood.
• Self-learning models can corrupt data or otherwise make it unreadable.

Which of the following is a transparency risk of closed source software?

• Closed source software includes obfuscated code that cannot be read by a human.
• Closed source software cannot be shared with business partners.
• Closed source software cannot be reviewed by the organization that developed it.
• Closed source software may not be accessible to independent auditors.

A disruptive user on a social media site is subjected to a shadow ban. Which of the following might be an indication of that shadow ban?

• A user logs in one day to find a message from a site administrator saying that the user has been banned.
• A user logs in one day to find that they have been asked to discontinue their disruptive behavior, or they will be banned.
• A user logs in one day to find that their posting privileges have been revoked.
• A user logs in one day to find that they are able to post, but receive no direct responses.

Which of the following is an effort to turn black box AI models into models whose decisions are easier to understand?

• Explainable AI
• Human-in-the-loop
• Self-learning models
• Neural networks

You want to solicit feedback from users who are seeking explanations about your AI products and services. So, you decide to place a form on your marketing website that users can fill out. Which of the following is the best way to structure that form for the purpose of collecting useful feedback?

• Provide a series of yes or no questions with radio buttons where users select their respective answers.
• Provide a large, unrestricted text box where users can enter their thoughts at length.
• Provide a series of open questions with a single-line entry field where users can provide short answers.
• Provide a drop-down menu of feedback categories that users can select from, with a promise that you'll follow up via email.

You're the recipient of some data collected by a third party that you'll use in training an AI model. As per your business agreement, the third-party discloser of the data requests that you explain how you plan to use the data. At what point in the process should you provide this explanation?

• At the point of collecting the data.
• At the point of evaluating the model.
• At the point of training the model.
• At the point of planning the AI system.

Which of the following are potential training data inadequacies that you should communicate to your users in support of transparency? (Select two.)

• The amount of time it took to collect the data.
• Any missing values in the dataset and how they were handled.
• The relatively large size of a dataset used in training.
• Any known bias in the sample data.

Which of the following is a technique used by the Python tool Alibi to produce a subset of features that will usually result in the same model prediction?

• Anchor Explanations
• Shapley value
• Local Interpretable Model-Agnostic Explanations
• Perturbation

Which of the following Python tools is designed to integrate with Google's Cloud AI platform?

• LIME
• What-If
• ELI5
• SHAP

Which of the following are typically true when comparing the LIME tool with the SHAP tool? (Select two.)

• LIME outputs results faster than SHAP.
• LIME is less accurate than SHAP.
• LIME supports fewer types of models than SHAP.
• LIME supports more programming languages than SHAP.