Capstone Project Class 12 MCQ Online Test

Students find these Class 12 AI MCQ Chapter 1 Capstone Project Class 12 MCQ Online Test with Answers helpful for self-assessment and preparation.

Class 12 AI Capstone Project MCQ

MCQ on Capstone Project Class 12

Class 12 Capstone Project MCQ – Capstone Project MCQ Class 12

Multiple Choice Questions

Question 1.
Every AI project múst undergo ________ steps?
a. 3
b. 4
c. 5
d. 6
Answer:
d. 6

Question 2.
Which of the following statement is true about design thinking methodology
a. It provides a solution-based approach to solve problems
b. It is useful to tackle complex problems
c. It is a practical approach to protyping
d. All of the above
Answer:
d. All of the above

Question 3.
How many stages are there in design thinking framework.
a. 3
b. 4
c. 5
d. 6
Answer:
c. 5

Question 4.
A researcher wants to study the association between gender and using a mobile phone. Data collected for this study will be ____.
a. Qualitative data
b. Quantitative data
c. Continuous data
d. Classified data
Answer:
b. Quantitative data

Question 5.
Primary way to collect DATA (Data Gathering process)?
a. Experiment
b. Survey
c. Interview
d. Observation
Answer:
b. Survey

Question 6.
Which of the following is not a regression loss function
a. Exponential loss
b. Mean absolute error
c. Mean square error
d. Quantile loss
Answer:
a. Exponential loss

Question 7.
The data scientist will use _____ for predictive modelling?
a. Artificial Intelligence
b. Machine Learning
c. Training Set
d. Deep Learning
Answer:
c. Training Set

Question 8.
Which one does NOT belong with Classification loss?
a. Log loss
b. Mean Absolute Error
c. Exponential Loss
d. Hinge Loss
Answer:
b. Mean Absolute Error

Question 9.
Which process does NOT come under Capstone Project?
a. AI Model
b. AI Project Cycle
c. Deployment
d. Data Gathering
Answer:
b. AI Project Cycle

Question 10.
Which one does NOT belong with Regression loss?
a. Log Loss
b. Mean Absolute Error
c. Log cosh Loss
d. Quantile Loss
Answer:
a. Log Loss

Question 11.
Adding a non-important feature to a linear regression model may result in.
1) Increase in R -square
2) Decrease in R-square
a. Only 1 is correct
b. Only 2 is correct
c. Either 1 or 2
d. Neither 1 nor 2
Answer:
a. Only 1 is correct

Question 12.
Which of the following options is/are true for K-fold cross-validation?
1) Increase in K will result in higher time required to cross validate the result.
2) Higher values of K will result in higher confidence on the cross-validation result as compared to lower value of K.
3) If K = N, then it is called Leave one out cross validation, where N is the number of observations
a. 1 and 2
b. 2 and 3
c. 1 and 3
d. 1,2 and 3
Answer:
d. 1,2 and 3

Question 13.
Choose Correct Option
a. Data Requirements >> Data Collection >> Data understanding >> Data preparation
b. Data Requirements >> Data understanding >> Data Collection >> Data preparation
c. Data Requirement >> Data Deployment >> Data Collection >> Data Gathering
d. Data Collection >> Data Request >> Data Filtering >> Data Evaluation
Answer:
a. Data Requirements >> Data Collection >> Data understanding >> Data preparation

Question 14.
In AI development which framework is used?
a. Scikit-learn
b. Tensorflow
c. PyCharm
d. Matplotlib
Answer:
b. Tensorflow

Question 15.
If your Neural Network model seems to have high variance, what of the following would be promising things to try?
a. Make the Neural Network deeper
b. Get more training data
c. Get more test data
d. Increase the number of units in each hidden layer
Answer:
b. Get more training data

Question 16.
Which stage in Design Thinking missing [Prototype, Ideate, Test, Define]
a. Evaluation
b. Empathies
c. Evolution
d. Enrichment
Answer:
b. Empathies

Question 17.
Which language is Most suitable for developing AI?
a. Kotlin
b. Swift
c. Python
d. HTML
Ans,
c. Python

Question 18.
A random sample of n=6 taken from the population has the elements 6,10,13,14,18,20. Then, which option is False?
a. Point estimate for population mean is 13.5
b. Point estimate for population standard deviation is 4.68
c. Point estimate for population standard deviation is 3.5
d. Point estimate for standard error of mean is 1.91
Answer:
c. Point estimate for population standard deviation is 3.5

Question 19.
The following data is used to apply a linear regression algorithm with least squares regression line Y = a1 X. Then, the approximate value of a1 is given by:(XIndependent variable, Y -Dependent variable)

a. 27.876
b. 32.650
c. 40.541
d. 28.956
Answer:
d. 28.956

Question 20.
Which of the following statements is/are INCORRECT
i) The volume of test data can be large, which presents complexities.
ii) Your testing team should test the AI and ML algorithms keeping model validation, successful learn ability, and algorithm effectiveness in mind.
iii) Test data should include all irrelevant subsets of training data, i.e., the data you will use for training the AI system.
a. None of the Below
b. ii)
c. iii)
d. i),ii) & iii)
Answer:
c. iii)

Question 21.
Which of these is NOT analytic based on type of question?
a. Descriptive
b. Statistical Analysis
c. Forecasting
d. Data evaluation
Answer:
d. Data evaluation

Question 22.
A researcher wants to study the association between gender and using a mobile phone. Data collected for this study will be ________.
a. Qualitative data
b. Quantitative data
c. Continuous data
d. Classified data
Answer:
b. Quantitative data

Question 23.
If a models RMSE value is 160 then ______.
a. It is a bad model
b. The model performance is high
c. There many mistakes in the model
d. The model is average
Answer:
b. The model performance is high

Question 24.
Which of the following function in the scikit-learn python machine learning package is used to implement train-test split evaluation procedure?
a. Train_test()
b. Test_split()
c. Train_split()
d. Train_test_split()
Answer:
d. Train_test_split()

Question 25.
How many types of validation methods are there?
a. 2
b. 3
c. 4
d. 5
Answer:
a. 2

Question 26.
In data science methodology how many stages are there?
a. 7
b. 8
c. 9
d. 10
Answer:
d. 10

Question 27.
In this stage “The analytical methods require some content, format, and initial data collection” here we are talking about which stage of data science methodology in analytics approach.
a. Data requirements
b. Data collection
c. Data understanding
d. Data preparation
Answer:
a. Data requirements

Question 28.
“Data scientist can use statistical significance test to verify the models accuracy”. Here we are talking about which stage of analytics approach in data science methodology
a. Modelling
b. Evaluation
c. Deployment
d. Feedback
Answer:
b. Evaluation

Question 29.
In this stage “Data cleansing, combining data from multiple sources and the conversation of data to form a more useful data is done”. Here we are talking about which stage of analytics approach?
a. Deployment
b. Modelling
c. Data preparation
d. Evaluation
Answer:
c. Data preparation

Question 30.
Whose value should be less than 180 for good performance AI model.
a. Mean square error
b. Root mean square error
c. Mean absolute error
d. None of the above
Answer:
b. Root mean square error

Question 31.
Which of the following is not an example of hyper parameters?
a) Train-test split ratio
b) Number of hidden layers in a Neural Network
c) Number of clusters in a clustering task
d) learning rate in random forest
Answer:
d) learning rate in random forest

[Explanation: Learning rate is not an hyper parameter in random forest, as increase in the number of tree will cause under fitting]

Question 32.
Which of the following statements is true for Mean Squared Error (MSE) in regression?
a. MSE is the sum of squared distances between our target variable and predicted values.
b. MSE is the sum of the cube of distance between our target variable and predicted values.
c. MSE is the sum of distances between our target variable and predicted values.
d. MSE is the sum of distances between our median and mean values.
Answer:
a. MSE is the sum of squared distances between our target variable and predicted values.

Question 33.
Which of the following is the reason to use Mean Squared Error (MSE)?
a. It cannot be compared to Mean Absolute Error.
b. It is sensitive towards outliers.
c. It is good to use if the target data is not distributed around the mean value.
d. The range of MSE is between o to 1.
Answer:
b. It is sensitive towards outliers.

Question 34.
The data scientist will use a………..for predictive modeling.
a. Algorithm
b. Training set
c. Data compilation
d. Data preparation
Answer:
b. Training set

Question 35.
Design thinking is a design methodology that provides a………approach to solving problems.
a. Problem-based
b. Solution-based
c. Analysis-based
d. Approach-based
Answer:
b. Solution-based

Question 36.
Which stage in design thinking is missing [Prototype, Ideate, Test, Define]
a. Evaluation
b. Empathies
c. Evolution
d. Enrichment
Answer:
b. Empathies

Question 37.
In ……….. we run our modeling process on different subsets of the data to get.
a. Train-test split
b. Cross-validation
c. Machine learning
d. Validation
Answer:
b. Cross-validation

Question 38.
Techniques such as descriptive statistics and- ……… can be applied to the dataset, to assess the content, quality and initial insights about the data.
a. Visualization
b. Evaluation
c. Modeling
d. Analysis
Answer:
a. Visualization

Question 39.
Regression functions predict a———–and classification predicts a label.
a. Output
b. Quantity
c. Loss
d. Logic
Answer:
b. Quantity

Question 40.
If your neural model seems to have high variance, what of the following would be promising things to try?
a. Make the neural network deeper
b. Get more training data
c. Get more test data
d. Increase the number of units in each hidden layer
Answer:
b. Get more training data

Question 41.
Match the following
1) Which category? A. (Anomaly Detection)
2) How much or how many? B. (Regression)
3) Which group? C. (Recommendation)
4) Is this unusual? D. (Classification)
5) Which option should be taken? E. (Clustering)
a) 1=D, 2=B, 3=E, 4=A, 5=C
b) 1=C, 2=D, 3=B, 4=E, 5=A
c) 1=D, 2=B, 3=C, 4=E, 5=A
d) 1=E, 2=A, 3=D, 4=C, 5=B
Answer:
a) 1=D, 2=B, 3=E, 4=A, 5=C

Question 42.
Identify two AI development tools from the following:
1) DataRobot
2) Python
3) Scikit Learn
4) Watson Studio
(a) 1 & 2
(b) 2 & 3
(c) 1 & 3
(d) 1 & 4
Answer:
(d) 1 & 4

Question 43.
You want to predict future house prices. The price is a continuous value, and therefore we want to do regression. Which loss function should be used here?
(a) RMSE
(b) MSE
(c ) Exponential error
(d) MAE
Answer:
(b) MSE

Question 44.
Techniques like descriptive statistics and visualizations can be applied to datasets after the original data gathering to analyze the content. To close the gap, additional data collecting may be required. Identify the stage of this analytic approach.
(a) Data Requirements
(b) Data Gathering
(c) Data Understanding
(d) Data Preparation
Answer:
(c) Data Understanding

Question 45.
Which of the following is not a feature of RMSE?
(a) It tells about the accuracy of the model.
(b) Higher value means hyper parameters need to be tweaked
(c) Lower RMSE values are not good for the AI model.
(d) RMSE is a measure of how evenly distributed residual errors are.
Answer:
(c) Lower RMSE values are not good for the AI model.

Question 46.
Once you have got an AI model that’s ready for production, AI engineers then _______ a trained model, making it available for external inference requests.
(a) Evaluate
(b) Test
(c) Deploy
(d) Redesign
Answer:
(c) Deploy

Question 47.
Which of the following is a disadvantage of Cross Validation Technique?
(a) Cross-validation provides insight into how the model will generalize to a new dataset.
(b) Cross-validation aids in determining a more accurate model prediction performance estimate.
(c) As we need to train on many training sets, cross-validation is computationally expensive.
(d) Cross-validation could result in more precise models.
Answer:
(c) As we need to train on many training sets, cross-validation is computationally expensive.

Question 48.
Hyper parameters are parameters whose values govern the learning process.
(a) True
(b) False
Answer:
(a) True

Question 49.
Choose the difference between Regression and Classification Loss functions from the following:
(a) Regression functions predict a quantity, and classification functions predict a label.
(b) Regression functions predict a label, and classification functions predict a quantity.
(c) Regression functions predict a qualitative value, and classification functions predict a label.
(d) Regression functions predict a label, and classification functions predict a qualitative value.
Answer:
(a) Regression functions predict a quantity, and classification functions predict a label.

Question 50.
A good model should have an _______ value less than 180 .
(a) RMSE
(b) MSE
(c) Focal Loss
(d) MAE
Answer:
(a) RMSE

Question 51.
Which of the following is incorrect?
1) Testing data is the one on which we train and fit our model basically to fit the parameters
2).Training data is used only to assess performance of model
3) Testing data is the unseen data for which predictions have to be made
a) 1) and 3) only
b) 1) and 2) only
c) 2) and 3) only
d) 1), 2) and 3)
Answer:
b) 1) and 2) only

Question 52.
Which of the following are the objectives of the testing team in AI modelling?
1) Model Validation
2) Security compliance
3) Understanding data
4) Minimizing bias
a. (1), (2) and (3)
b. (2), (3) and (4)
c. (1), (3) and (4)
d. (1), (2) and (4)
Answer:
d. (1), (2) and (4)

Question 53.
If AI techniques are to be applied to a dataset, the data must have a _______ .
a. association
b. relationship
c. pattern
d. Either a and b
Answer:
c. pattern

Question 54.
Define capstone project.
Answer:
A capstone project is a task that requires students to conduct independent research on a subject in order to gain a thorough understanding of it. It offers the student the chance to put all of their knowledge together and show it through an extensive project.

Question 55.
Can MSE be a negative value? Give reasons.
Answer:
A negative MSE value is impossible. Projected and actual value differences are always squared. Therefore, every result is either positive or negative.

Fill in the Blanks:

Question 1.
MSE value can be a-
Answer:
Positive or zero

Question 2.
_______ is also known as ‘top-level’ parameters that regulate the learning process.
Answer:
Hyper parameters

Question 3.
_______ method is a metric for determining how well a regression line fits the data points.
Answer:
Root Mean Square Error(RMSE)

Question 4.
To predict future of house prices, _______ can be used as the loss function.
Answer:
MSE
[Hint: as the Price is a continuous value]

Question 5.
_______ function predicts a quantity.
Answer:
Regression

Question 6.
_______ function predicts a label.
Answer:
Classification

Question 7.
The last stage in the methodology is-
Answer:
Feedback

Question 8.
For smaller dataset _______ method is used for validation.
Answer:
cross-validation

Question 9.
_______ validation procedure runs faster and useful for large datasets.
Answer:
Train_test _split()

Question 10.
To compare two model qualities, we use _______ method.
Answer:
Mean Absolute error (MAE)

State True or False:

Question 1.
If you have a large RMSE value, most likely you can alter your hype parameters.
Answer:
True

Question 2.
We can have negative Mean Absolute Error value.
Answer:
true

Question 3.
RMSE Root Mean Square Method can be negative.
Answer:
False

Question 4.
Once the model has been developed and approved by business clients as well as stake holders, it is deployed into the market.
Answer:
True

Question 5.
The shortcoming of train-test split is it cannot perform well on small datasets.
Answer:
True

Assertion-Reasoning Based Questions

Study the two statements labeled as assertion (a) and reason (r).
Point out if:
(a) Both, a and r, are true and r is the correct explanation of a
(b) Both, a and r, are true but r is not the correct explanation of a
(c) If a is true but r is false
(d) If a is false but r is true
(e) Both A and R are false.

Question 1.
Assertion(A): A capstone project is a project where students must research a topic independently in order to gain a deep understanding of the subject content.
Reason (R): Through this a student’s knowledge to a particular subject can be evaluated or tested.
Answer:
(a) Both, a and r, are true and r is the correct explanation of a

Question 2.
Assertion (A): Every AI project follows six steps: Problem definition, data collection, feature definition, AI model construction, Evaluation, and deployment.
Reason (R): There is no AI solution for everything.
Answer:
(b) Both, a and r, are true but r is not the correct explanation of a

Question 3.
Assertion (A): Problem definition is the initial stage of the problem.
Reason (R): In this stage it is decided, whether operation of artificial intelligence is the solution to the problem or not.
Answer:
(a) Both, a and r, are true and r is the correct explanation of a

Question 4.
Assertion(A): In the model evaluation stage, quality of the model is assessed. The model undergoes diagnostic measure phases and statistical significance testing phase.
Reason(R): Model evaluation stage does not help in interpreting the efficacy of the model.
Answer:
(c) If a is true but r is false

Question 5.
Assertion(A): The used data is splitted into three categories: model data, training data and testing data.
Answer:
(d) If a is false but r is true

Case-Based Questions:

Question 1.
Mohan wants to create his first app so he went to a vendor and asked for a help. The vendor asked a set of questions as written below :
What kind of app you want to create?
What will your app will look like?
Who is the target audience for your app?
What will the graphics will look like?
What audio will you include?
What software will you use to build your app?
How will the user navigate your app?
How will you test your app?
What do you think the questions are legitimate or not?
Answer:
Yes the questions are very legitimate unless, this questions are asked task cannot be decomposed into a series of smaller problems and then the solution of the problem could be found out.

Question 2.
Simran got RMSE value of a model is 150 but she is confused whether the model performance is good or not, help her in understanding this.
Answer:
Here RMSE value is less than 180 so it has less mistakes and when the RMSE value is low then it is considered the models performance is high. Thus it is a good model.

Question 3.
Suman wants to work on AI framework as she is keen to make a model, that will periodically track her child’s education system. But, she doesn’t have much knowledge about it, so she consulted her friend the best framework out of the following frameworks. Help her in getting out from confusion.
a. Scikit-learn
b. TensorFlow
c. PyCharm
d. Matplotlib
Answer:
b. TensorFlow

The post Capstone Project Class 12 MCQ Online Test appeared first on Learn CBSE.