wayground logo

Free Printable Worksheets

NEW

Font size

S
M
L
XL
Worksheets

MS Champ Month of Jan

Total questions: 15

Worksheet time: 8mins

Name
Class
Date
1.

What is Responsible AI?

a)

a) An approach to developing AI safely and ethically

b)

b) A new machine-learning algorithm

c)

c) A type of neural network architecture

d)

d) A dashboard for analyzing models

2.

Which of these is not one of the six principles of Microsoft's Responsible AI Standard? 

a)

a) Fairness

b)

b) Reliability & Safety

c)

c) Accuracy

d)

d) Inclusiveness

3.

What does the Responsible AI Dashboard provide? 

a)

a) Access Azure Open AI Services

b)

b) Automated model training 

c)

c) Data labelling

d)

d) A central place to access Responsible AI tools

4.

What are some components of the Responsible AI Dashboard?

a)

a) Model debugging and business decision-making tools

b)

b) Data visualization and database management 

c)

c) Automated data labelling and augmentation

d)

d) Neural architecture search and hyperparameter tuning

5.

How can you find model performance inconsistencies? 

a)

a) Compare metrics across cohorts

b)

b) Analyze probability distributions

c)

c) Visualize performance scores  

d)

d) All of these

6.

What are some reasons to use the Responsible AI Dashboard?  

a)

a) Centralize access to Responsible AI tools 

b)

b) Streamline workflows

c)

c) Improve tool integration

d)

d) All of these

7.

What do most of the traditional ML metrics focus on?  

a)

a) Ratio of correct vs incorrect predictions

b)

b) Training time

c)

c) Loss function values

d)

d) Number of parameters

8.

What metrics can show model performance for a cohort? 

a)

a) Accuracy, Precision, Recall, MAE, RMSE

b)

b) Learning rate, batch size, epochs 

c)

c) Loss, gradient norm, step size

d)

d) Flops, latency, throughput

9.

What can probability distributions show? 

a)

a) Uncertainty estimates

b)

b) The distribution of a cohort's predicted outcomes

c)

c) Decision Boundaries

d)

d) Feature importance

10.

Model explainability can help with:  

a)

a) Compliance and auditing

b)

b) Identifying biases

c)

c) Increasing transparency

d)

d) All of these

11.

The Responsible AI Dashboard provides: 

a)

a) Unified access to Responsible AI tools

b)

b) Automated pipeline creation

c)

c) Hyperparameter optimization

d)

d) Neural architecture search

12.

When should you create a Responsible AI Dashboard? 

a)

a) Before training a model

b)

b) During data collection

c)

c) After developing a model

d)

d) Before deployment

13.

What are common issues that the Dashboard can uncover? 

a)

a) Biases, errors, unintended correlations

b)

b) Underfitting, vanishing gradients

c)

c) Class imbalance, label noise

d)

d) High bias, high variance

14.

The Dashboard tools can help: 

a)

a) Improve model safety and reliability

b)

b) Speed up training

c)

c) Simplify deployment

d)

d) Reduce inference latency  

15.

Who can benefit from using the Dashboard?

a)

a) Data scientists

b)

b) Developers

c)

c) Business decision-makers 

d)

d) All of these