CT-AI試験無料問題集（162題）「ISTQB Certified Tester AI Testing 認定」

出題：1

Which ONE of the below types of testing is NOT a type of experience based testing applied to an AI based system?

A. Using knowledge about previous ML systems to identify potential biases

B. Using an industry checklist to assess the steps used to prepare an ML system

C. Exploring training data to understand its variety, patterns, structure and shape - then using that to inform testing

D. Usability testing of the format of the output predictions

正解：D 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：2

Which of the following is an example of overfitting?

A. The model is too simplistic for the data

B. The model is not able to generalize to accommodate new types of data

C. The model discards data it considers to be noise or outliers

D. The model is missing relationships between the inputs and outputs

正解：B 解答を投票する

出題：3

Consider a natural language processing (NLP) algorithm that attempts to predict the next word that you would like to type in a text message. An update to the algorithm has been created that should increase the accuracy of the predictions based on user typing patterns. The old algorithm was rated for accuracy by the users. Then, after the new update was released, the users rated the updated algorithm. A statistical test was used to compare the two versions of the algorithm to see whether or not the update should remain in place.
This is an example of what type of testing?

A. Pairwise testing

B. Exploratory testing

C. Metamorphic testing

D. A/B testing

正解：D 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：4

How can a tester check the system for bias as part of a review of data sources, acquisition, and preprocessing?
Choose ONE option (1 out of 4)

A. During the review of the preprocessing, the auditor can uncover whether the data has been influenced in a way that could lead to sample distortions.

B. It may use the LIME method as part of its data collection review to detect inappropriate bias.

C. As part of the review of preprocessing, it can reveal whether the data has been influenced in a way that could lead to algorithmic bias.

D. During the review, it can uncover algorithmic bias by analysing the procedures used to obtain the training data.

正解：A 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：5

Which statement about automation bias is correct?
Choose ONE option (1 out of 4)

A. When testing AI-based systems, automation bias does not play a role in supporting test activities such as boundary value analysis

B. Automation bias particularly affects testing of autonomous systems

C. Automation bias is tested with representative users, but human input quality is irrelevant

D. Automation bias affects the testing of AI-based systems that support users in their actions or decisions

正解：D 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：6

Which ONE of the below is NOT an input to an activation function in a neural network?

A. Activation values form the current layer

B. Bias

C. The weights assigned to the connections

D. Activation values from the previous layer

正解：A 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：7

A wildlife conservation group would like to use a neural network to classify images of different animals. The algorithm is going to be used on a social media platform to automatically pick out pictures of the chosen animal of the month. This month's animal is set to be a wolf. The test team has already observed that the algorithm could classify a picture of a dog as being a wolf because of the similar characteristics between dogs and wolves. To handle such instances, the team is planning to train the model with additional images of wolves and dogs so that the model is able to better differentiate between the two.
What test method should you use to verify that the model has improved after the additional training?

A. Adversarial testing to verify that no incorrect images have been used in the training

B. Back-to-back testing using the version of the model before training and the new version of the model after being trained with additional images

C. Metamorphic testing because the application domain is not clearly understood at this point

D. Pairwise testing using combinatorics to look at a long list of photo parameters

正解：B 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：8

Which ONE of the following options BEST DESCRIBES clustering?
SELECT ONE OPTION

A. Clustering is classification of a continuous quantity.

B. Clustering is supervised learning.

C. Clustering is done without prior knowledge of output classes.

D. Clustering requires you to know the classes.

正解：C 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：9

Which ONE of the following activities is MOST relevant when addressing the scenario where you have more than the required amount of data available for the training?
SELECT ONE OPTION

A. Feature selection

B. Data sampling

C. Data augmentation

D. Data labeling

正解：B 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：10

A data scientist is performing unsupervised learning on a set of financial records relating to previous loan applications, and trying to predict defaults on future loans. They are reporting poor functional performance because of data issues. Which ONE of the below is LEAST likely to be a contributory factor?

A. Irrelevant data included in the account records

B. Missing data relating to whether loans were previously granted and repaid

C. Inconsistent pre-processing of some records

D. Missing records for some accounts

正解：B 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：11

Which ONE of the below statements BEST describes how combinatorial testing can be applied to AI based systems?

A. Inputs to the system and environment factors can be considered parameters for pairwise tests

B. Combinatorial testing cannot yet be applied to AI

C. Each neuron can be treated as a parameter for pairwise tests

D. Two variants of the system can be used and compared

正解：A 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：12

Which of the following is an example of overfitting?

A. The model is too simplistic for the data

B. The model is not able to generalize to accommodate new types of data

C. The model discards data it considers to be noise or outliers

D. The model is missing relationships between the inputs and outputs

正解：B 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：13

The following confusion matrix represents the functional performance of a classifier.

Which ONE of the following is the correct calculation for the accuracy of the classifier?

A. 2 * (60 / (60 + 20) * 60 / (60 + 9)) / (60 / (60 + 20) + 60 / (60 + 9)) * 100% = 80%

B. 3 60/ (60 + 9)' 100% = 87%

C. 60 / (60 * 20) * 100% = 75%

D. (60+ 11) / (60 + 11 + 20+ 9) * 100%-71%

正解：D 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：14

An engine manufacturing facility wants to apply machine learning to detect faulty bolts. Which of the following would result in bias in the model?

A. Selecting testing data from a boat manufacturer's bolt longevity data

B. Selecting testing data from a different dataset than the training dataset

C. Selecting training data purposely excluding specific faulty conditions

D. Selecting training data by purposely including all known faulty conditions

正解：C 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：15

Which ONE of the following options does NOT describe a challenge for acquiring test data in ML systems?
SELECT ONE OPTION

A. Nature of data constantly changes with lime.

B. Data for the use case is being generated at a fast pace.

C. Test data being sourced from public sources.

D. Compliance needs require proper care to be taken of input personal data.

正解：B 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

CT-AI試験無料問題集「ISTQB Certified Tester AI Testing 認定」