[Sep 22, 2026] Get Unlimited Access to CT-AI Certification Exam Cert Guide
Reliable Study Materials for CT-AI Exam Success For Sure
NEW QUESTION # 83
Which ONE of the following options is an example that BEST describes a system with Al-based autonomous functions?
SELECT ONE OPTION
- A. A system that utilizes a tool like Selenium.
- B. A system that utilizes human beings for all important decisions.
- C. A system that is fully able to respond to its environment.
- D. A fully automated manufacturing plant that uses no software.
Answer: C
Explanation:
* AI-Based Autonomous Functions: An AI-based autonomous system is one that can respond to its environment without human intervention. The other options either involve human decisions or do not use AI at all.
* Reference: ISTQB_CT-AI_Syllabus_v1.0, Sections on Autonomy and Testing Autonomous AI-Based Systems.
NEW QUESTION # 84
Which of the following neural network coverage criteria can be adapted for its application?
Choose ONE option (1 out of 4)
- A. Sign-Sign coverage
- B. Sign-Change coverage
- C. Threshold coverage
- D. Neuron coverage
Answer: C
Explanation:
Section4.2 - Test Coverage Criteria for AI Modelsof the ISTQB CT-AI syllabus describes neural network- specific coverage methods. Among the techniques,threshold coverageis explicitly noted asadaptable, meaning testers may choose different thresholds to determine whether neuron activation is considered "covered." This flexibility makes threshold coverage adjustable to the model architecture, problem domain, and required test thoroughness.
Options A and B (Sign-Sign and Sign-Change coverage) are more rigid structural criteria and are not described as adaptable within the syllabus. They focus on sign patterns of neuron activations and do not allow altering thresholds. Option D, neuron coverage, measures the proportion of neurons activated at least once.
Although simple, it is not defined as an adaptable criterion. Its limitations are documented: it provides shallow insight and too easily achieves high coverage.
Onlythreshold coverageallows testers to adjust activation thresholds for more refined coverage measurement, makingOption Cthe correct choice.
NEW QUESTION # 85
Which of the following is an example of a clustering problem that can be resolved by unsupervised learning?
- A. Associating shoppers with their shopping tendencies
- B. Classifying muffin purchases based on the perceived attractiveness of their packaging
- C. Grouping individual fish together based on their types of fins
- D. Estimating the expected purchase of cat food after a particularly successful ad campaign
Answer: A
Explanation:
Clustering is a form ofunsupervised learning, which groups data points based onsimilarities without predefined labels. According toISTQB CT-AI Syllabus, clustering is used in scenarios where:
* The objective is to find natural groupings in data.
* The dataset does not have labeled outputs.
* Patterns and structures need to be identified automatically.
Analyzing the answer choices:
* A. Associating shoppers with their shopping tendencies # Correct
* Shoppers can be grouped based on purchasing behaviors(e.g., luxury shoppers vs. budget- conscious shoppers), which is a typical clustering application in market segmentation.
* B. Grouping individual fish together based on their types of fins # Incorrect
* If thetypes of fins are labeled, it becomes aclassification problem, which requires supervised learning.
* C. Classifying muffin purchases based on packaging attractiveness # Incorrect
* Classification, not clustering, because attractiveness scores or labels must be predefined.
* D. Estimating the expected purchase of cat food after an ad campaign # Incorrect
* This is a prediction task, best suited forregression models, which are part of supervised learning.
Thus,Option A is the best answer, asclusteringis used togroup shoppers based on tendencies without predefined labels.
Certified Tester AI Testing Study Guide References:
* ISTQB CT-AI Syllabus v1.0, Section 3.1.2 (Unsupervised Learning - Clustering and Association)
* ISTQB CT-AI Syllabus v1.0, Section 3.3 (Selecting a Form of ML - Clustering).
NEW QUESTION # 86
Which of the following decisions is BEST as a test approach for the described situation?
Choose ONE option (1 out of 4)
- A. You execute the test cases from the old camera model at the integration test level; no further dynamic tests of the operating data pipeline are necessary.
- B. You plan to perform reviews and exploratory data analysis of the image data sets to reduce the risk of a lack of representativeness of this data.
- C. You plan experience-based testing by the entire team at the system test level to ensure that the end users are satisfied.
- D. You plan to manually execute regular regression tests of the new camera function, particularly for system tests.
Answer: C
Explanation:
The ISTQB CT-AI syllabus emphasizes that testing AI-based systems requirescross-functional collaboration andexperience-based testingwhen parts of the team lack domain knowledge. In this scenario, the ML expert understands ML and dataset preparation but lacks knowledge ofcamera system behavior, the device's operational data pipeline, and end-user workflows. The remainder of the team understands the domain and system testing but not ML. Section4.4 - Human Factors and AI Testingand4.3 - System Testing of AI Componentshighlight that when domain understanding is unevenly distributed,experience-based testing conducted by the full team(testers, developers, domain experts) is the most effective approach. This ensures that AI outputs align with actual user expectations and system behavior. OptionCaligns exactly with this principle.
Option A is too limited and does not address the need to validate ML integration. Option B is incorrect because reusing old test cases overlooks AI-specific risks in the operating data pipeline. Option D is useful but focuses only on data representativeness, not system-level user validation. Therefore,Option Cis the best, syllabus-aligned test approach.
NEW QUESTION # 87
An e-commerce developer built an application for automatic classification of online products in order to allow customers to select products faster. The goal is to provide more relevant products to the user based on prior purchases.
Which of the following factors is necessary for a supervised machine learning algorithm to be successful?
- A. Selecting the correct data pipeline for the ML training
- B. Minimizing the amount of time spent training the algorithm
- C. Labeling the data correctly
- D. Grouping similar products together before feeding them into the algorithm
Answer: C
Explanation:
Supervised machine learning requires correctly labeled data to train an effective model. The learning process relies on input-output mappings where each training example consists of an input (features) and a correctly labeled output (target variable). Incorrect labeling can significantly degrade model performance.
* Supervised Learning Process
* The algorithm learns from labeled data, mapping inputs to correct outputs during training.
* If labels are incorrect, the model will learn incorrect relationships and produce unreliable predictions.
* Quality of Training Data
* The accuracy of any supervised ML model ishighly dependent on the quality of labels.
* Poorly labeled data leads to mislabeled training sets, resulting inbiased or underperforming models.
* Error Minimization and Model Accuracy
* Incorrectly labeled data affects theconfusion matrix, reducing precision, recall, and accuracy.
* It leads to overfitting or underfitting, which decreases the model's ability to generalize.
* Industry Standard Practices
* Many AI development teams spend a significant amount of time ondata annotation and quality controlto ensure high-quality labeled datasets.
* (B) Minimizing the amount of time spent training the algorithm#(Incorrect)
* While reducing training time is important for efficiency, the quality of training is more critical. A well-trained model takes time to process large datasets and optimize its parameters.
* (C) Selecting the correct data pipeline for the ML training#(Incorrect)
* A good data pipeline helps, butit does not directly impact learning successas much as labeling does.Even a well-optimized pipeline cannot fix incorrect labels.
* (D) Grouping similar products together before feeding them into the algorithm#(Incorrect)
* This describesclustering, which is anunsupervised learning technique. Supervised learningrequires labeled examples, not just grouping of data.
* Labeled data is necessary for supervised learning."For supervised learning, it is necessary to have properly labeled data."
* Data labeling errors can impact performance."Supervised learning assumes that the data is correctly labeled by the data annotators.However, it is rare in practice for all items in a dataset to be labeled correctly." Why Labeling is Critical?Why Other Options are Incorrect?References from ISTQB Certified Tester AI Testing Study GuideThus,option A is the correct answer, ascorrectly labeled data is essential for supervised machine learning success.
NEW QUESTION # 88
Which of the following neural network coverage criteria can be adapted for its application?
Choose ONE option (1 out of 4)
- A. Sign-Sign coverage
- B. Sign-Change coverage
- C. Threshold coverage
- D. Neuron coverage
Answer: C
Explanation:
Section4.2 - Test Coverage Criteria for AI Modelsof the ISTQB CT-AI syllabus describes neural network- specific coverage methods. Among the techniques,threshold coverageis explicitly noted asadaptable, meaning testers may choose different thresholds to determine whether neuron activation is considered
"covered." This flexibility makes threshold coverage adjustable to the model architecture, problem domain, and required test thoroughness.
Options A and B (Sign-Sign and Sign-Change coverage) are more rigid structural criteria and are not described as adaptable within the syllabus. They focus on sign patterns of neuron activations and do not allow altering thresholds. Option D, neuron coverage, measures the proportion of neurons activated at least once.
Although simple, it is not defined as an adaptable criterion. Its limitations are documented: it provides shallow insight and too easily achieves high coverage.
Onlythreshold coverageallows testers to adjust activation thresholds for more refined coverage measurement, makingOption Cthe correct choice.
NEW QUESTION # 89
A bank wants to use an algorithm to determine which applicants should be given a loan. The bank hires a data scientist to construct a logistic regression model to predict whether the applicant will repay the loan or not. The bank has enough data on past customers to randomly split the data into a training data set and a test/validation data set. A logistic regression model is constructed on the training data set using the following independent variables:
* Gender
* Marital status
* Number of dependents
* Education
* Income
* Loan amount
* Loan term
* Credit score
The model reveals that those with higher credit scores and larger total incomes are more likely to repay their loans. The data scientist has suggested that there might be bias present in the model based on previous models created for other banks.
Given this information, what is the best test approach to check for potential bias in the model?
- A. A/B testing should be used to verify that the test data set does not detect any bias that might have been introduced by the original training data. If the two models significantly differ, it will indicate there is bias in the original model.
- B. Experienced-based testing should be used to confirm that the training data set is operationally relevant. This can include applying exploratory data analysis (EDA) to check for bias within the training data set.
- C. Acceptance testing should be used to make sure the algorithm is suitable for the customer. The team can re-work the acceptance criteria such that the algorithm is sure to correctly predict the remaining applicants that have been set aside for the validation data set ensuring no bias is present.
- D. Back-to-back testing should be used to compare the model created using the training data set to another model created using the test data set, if the two models significantly differ, it will indicate there is bias in the original model.
Answer: B
Explanation:
The syllabus mentions that experience-based testing and EDA are effective for detecting biases:
"Experience-based testing can be used to verify that the training dataset is operationally relevant and identify potential sources of bias. EDA is also useful for exploring the data and understanding any relationships that might lead to bias in the model."
NEW QUESTION # 90
Which ONE of the following is the BEST option to optimize the regression test selection and prevent the regression suite from growing large?
- A. Automating test scripts using Al-based test automation tools.
- B. Using of a random subset of tests.
- C. Identifying suitable tests by looking at the complexity of the test cases.
- D. Using an Al-based tool to optimize the regression test suite by analyzing past test results
Answer: D
Explanation:
This is the most effective approach as AI-based tools can analyze historical test data, identify patterns, and prioritize tests that are more likely to catch defects based on past results. This method ensures an optimized and manageable regression test suite by focusing on the most impactful test cases.
NEW QUESTION # 91
Which ONE of the following options does NOT describe an Al technology related characteristic which differentiates Al test environments from other test environments?
SELECT ONE OPTION
- A. The challenge of mimicking undefined scenarios generated due to self-learning
- B. The challenge of providing explainability to the decisions made by the system.
- C. Challenges resulting from low accuracy of the models.
- D. Challenges in the creation of scenarios of human handover for autonomous systems.
Answer: D
Explanation:
AI test environments have several unique characteristics that differentiate them from traditional test environments. Let's evaluate each option:
A . Challenges resulting from low accuracy of the models.
Low accuracy is a common challenge in AI systems, especially during initial development and training phases. Ensuring the model performs accurately in varied and unpredictable scenarios is a critical aspect of AI testing.
B . The challenge of mimicking undefined scenarios generated due to self-learning.
AI systems, particularly those that involve machine learning, can generate undefined or unexpected scenarios due to their self-learning capabilities. Mimicking and testing these scenarios is a unique challenge in AI environments.
C . The challenge of providing explainability to the decisions made by the system.
Explainability, or the ability to understand and articulate how an AI system arrives at its decisions, is a significant and unique challenge in AI testing. This is crucial for trust and transparency in AI systems.
D . Challenges in the creation of scenarios of human handover for autonomous systems.
While important, the creation of scenarios for human handover in autonomous systems is not a characteristic unique to AI test environments. It is more related to the operational and deployment challenges of autonomous systems rather than the intrinsic technology-related characteristics of AI .
Given the above points, option D is the correct answer because it describes a challenge related to operational deployment rather than a technology-related characteristic unique to AI test environments.
NEW QUESTION # 92
A word processing company is developing an automatic text correction tool. A machine learning algorithm was used to develop the auto text correction feature. The testers have discovered when they start typing "Isle of Wight" it fills in "Isle of Eight". Several UAT testers have accepted this change without noticing. What type of bias is this?
- A. Complacency/Disregard
- B. Geographical/Locality
- C. Automation/Complacency
- D. Ignorance/Cognitive
Answer: C
Explanation:
The syllabus describes automation bias as:
"A type of bias caused by a person favoring the recommendations of an automated decision- making system over other sources." This is also known as complacency bias, where testers accept automated system outputs without questioning them.
NEW QUESTION # 93
Which of the following is an example of overfitting?
- A. The model is missing relationships between the inputs and outputs.
- B. The model discards data it considers to be noise or outliers.
- C. The model is not able to generalize to accommodate new types of data.
- D. The model is too simplistic for the data.
Answer: C
Explanation:
Overfitting occurs when a machine learning (ML) model learns patterns that are too specific to the training data, leading to a lack of generalization for new, unseen data. This means the model performs exceptionally well on the training data but poorly on validation or test data because it has memorized the noise and minor details rather than learning the underlying patterns.
NEW QUESTION # 94
"AllerEgo" is a product that uses sell-learning to predict the behavior of a pilot under combat situation for a variety of terrains and enemy aircraft formations. Post training the model was exposed to the real- world data and the model was found to be behaving poorly. A lot of data quality tests had been performed on the data to bring it into a shape fit for training and testing.
Which ONE of the following options is least likely to describes the possible reason for the fall in the performance, especially when considering the self-learning nature of the Al system?
SELECT ONE OPTION
- A. There was an algorithmic bias in the Al system.
- B. The difficulty of defining criteria for improvement before the model can be accepted.
- C. The unknown nature and insufficient specification of the operating environment might have caused the poor performance.
- D. The fast pace of change did not allow sufficient time for testing.
Answer: B
Explanation:
* A. The difficulty of defining criteria for improvement before the model can be accepted.
* Defining criteria for improvement is a challenge in the acceptance of AI models, but it is not directly related to the performance drop in real-world scenarios. It relates more to the evaluation and deployment phase rather than affecting the model's real-time performance post-deployment.
* B. The fast pace of change did not allow sufficient time for testing.
* This can significantly affect the model's performance. If the system is self-learning, it needs to adapt quickly, and insufficient testing time can lead to incomplete learning and poor performance.
* C. The unknown nature and insufficient specification of the operating environment might have caused the poor performance.
* This is highly likely to affect performance. Self-learning AI systems require detailed specifications of the operating environment to adapt and learn effectively. If the environment is insufficiently specified, the model may fail to perform accurately in real-world scenarios.
* D. There was an algorithmic bias in the AI system.
* Algorithmic bias can significantly impact the performance of AI systems. If the model has biases, it will not perform well across different scenarios and data distributions.
Given the context of the self-learning nature and the need for real-time adaptability, optionAis least likely to describe the fall in performance because it deals with acceptance criteria rather than real-time performance issues.
NEW QUESTION # 95
The activation value output for a neuron in a neural network is obtained by applying computation to the neuron.
Which ONE of the following options BEST describes the inputs used to compute the activation value?
SELECT ONE OPTION
- A. Individual bias at the neuron level, and weights assigned to the connections between the neurons.
- B. Individual bias at the neuron level, activation values of neurons in the previous layer, and weights assigned to the connections between the neurons.
- C. Individual bias at the neuron level, and activation values of neurons in the previous layer.
- D. Activation values of neurons in the previous layer, and weights assigned to the connections between the neurons.
Answer: B
Explanation:
In a neural network, the activation value of a neuron is determined by a combination of inputs from the previous layer, the weights of the connections, and the bias at the neuron level. Here's a detailed breakdown:
* Inputs for Activation Value:
* Activation Values of Neurons in the Previous Layer:These are the outputs from neurons in the preceding layer that serve as inputs to the current neuron.
* Weights Assigned to the Connections:Each connection between neurons has an associated weight, which determines the strength and direction of the input signal.
* Individual Bias at the Neuron Level:Each neuron has a bias value that adjusts the input sum, allowing the activation function to be shifted.
* Calculation:
* The activation value is computed by summing the weighted inputs from the previous layer and adding the bias.
* Formula: z=#(wi#ai)+bz = \sum (w_i \cdot a_i) + bz=#(wi#ai)+b, where wiw_iwi are the weights, aia_iai are the activation values from the previous layer, and bbb is the bias.
* The activation function (e.g., sigmoid, ReLU) is then applied to this sum to get the final activation value.
* Why Option A is Correct:
* Option A correctly identifies all components involved in computing the activation value: the individual bias, the activation values of the previous layer, and the weights of the connections.
* Eliminating Other Options:
* B. Activation values of neurons in the previous layer, and weights assigned to the connections between the neurons: This option misses the bias, which is crucial.
* C. Individual bias at the neuron level, and weights assigned to the connections between the neurons: This option misses the activation values from the previous layer.
* D. Individual bias at the neuron level, and activation values of neurons in the previous layer: This option misses the weights, which are essential.
References:
* ISTQB CT-AI Syllabus, Section 6.1, Neural Networks, discusses the components and functioning of neurons in a neural network.
* "Neural Network Activation Functions" (ISTQB CT-AI Syllabus, Section 6.1.1).
NEW QUESTION # 96
A software component uses machine learning to recognize the digits from a scan of handwritten numbers. In the scenario above, which type of Machine Learning (ML) is this an example of?
SELECT ONE OPTION
- A. Reinforcement learning
- B. Clustering
- C. Regression
- D. Classification
Answer: D
Explanation:
Recognizing digits from a scan of handwritten numbers using machine learning is an example of classification. Here's a breakdown:
* Classification: This type of machine learning involves categorizing input data into predefined classes.
In this scenario, the input data (handwritten digits) are classified into one of the 10 digit classes (0-9).
* Why Not Other Options:
* Reinforcement Learning: This involves learning by interacting with an environment to achieve a goal, which does not fit the problem of recognizing digits.
* Regression: This is used for predicting continuous values, not discrete categories like digit recognition.
* Clustering: This involves grouping similar data points together without predefined classes, which is not the case here.
References:The explanation is based on the definitions of different machine learning types as outlined in the ISTQB CT-AI syllabus, specifically under supervised learning and classification.
NEW QUESTION # 97
Which ONE of the following approaches to labelling requires the least time and effort?
SELECT ONE OPTION
- A. Al-Assisted
- B. Pre-labeled dataset
- C. Outsourced
- D. Internal
Answer: B
Explanation:
* Labelling Approaches: Among the options provided, pre-labeled datasets require the least time and effort because the data has already been labeled, eliminating the need for further manual or automated labeling efforts.
* Reference: ISTQB_CT-AI_Syllabus_v1.0, Section 4.5 Data Labelling for Supervised Learning, which discusses various approaches to data labeling, including pre-labeled datasets, and their associated time and effort requirements.
NEW QUESTION # 98
Which ONE of the below statements BEST describes how combinatorial testing can be applied to AI based systems?
- A. Combinatorial testing cannot yet be applied to AI
- B. Two variants of the system can be used and compared
- C. Inputs to the system and environment factors can be considered parameters for pairwise tests
- D. Each neuron can be treated as a parameter for pairwise tests
Answer: C
Explanation:
The correct answer is C . The CT-AI syllabus explains that AI-based systems can have extremely high numbers of parameters, especially where they use big data or interact with the external world. Exhaustive testing of all parameter combinations is usually infeasible, so combinatorial techniques, especially pairwise testing, can reduce the number of required test cases while preserving useful defect detection capability.
The syllabus gives autonomous driving as an example, where high-level system tests should consider different operational environments and vehicle functions. Relevant parameters may include road types, surfaces, weather, traffic conditions, visibility, vehicle functions, and sensor effectiveness. This directly supports treating system inputs and environmental factors as parameters in pairwise tests.
Option A is not the intended application; neuron coverage is a neural-network coverage topic, not pairwise system scenario design. Option B describes A/B testing or back-to-back comparison, not combinatorial testing. Option D is false because the syllabus explicitly describes pairwise testing for AI-based systems and includes it as an examinable method.
References/topics: CT-AI Syllabus Chapter 9, Section 9.2 "Pairwise Testing."
=========
NEW QUESTION # 99
A facial recognition system is being deployed at airports in order to scan passengers' faces and compare them to a database of vaccinations, in order to identify unvaccinated passengers in a pandemic. There are a number of components involved including cameras, a model to segment the image, and a model to identify the face and match it against a known photograph. It is important that there are few false negatives, and that passengers cannot subvert the system. Which ONE of the following types of testing is the MOST appropriate options for the tests you would choose in system testing?
- A. Testing for concept drift
- B. Adversarial testing
- C. Testing for explainability
- D. Testing for transparency
Answer: B
Explanation:
The correct answer is B. Adversarial testing . The key risk in this scenario is deliberate subversion of the facial recognition process. The syllabus defines adversarial attacks as situations where an attacker subtly perturbs valid inputs passed to a trained model so that it produces incorrect predictions. It specifically notes that image classifiers can be misled by changes that may be invisible to the human eye, causing the model to classify an image incorrectly with high confidence.
This airport system uses cameras, segmentation, and face-matching models, so adversarial inputs could include manipulated facial images, masks, presentation attacks, lighting manipulation, or other perturbations intended to create false negatives. The syllabus states that adversarial testing performs adversarial attacks to identify vulnerabilities so that preventive measures can be taken. It also identifies adversarial testing as appropriate where mishandling adversarial examples could have significant impact or where the system may be attacked.
References/topics: CT-AI Syllabus Chapter 9, Sections 9.1.1 and 9.7; Chapter 7, Section 7.2.5 "System Testing."
=========
NEW QUESTION # 100
An ML engineer performing supervised learning needs to label images of football games based on the location of the football in the image. Which ONE of the below labelling approaches can be used?
- A. Augmentation
- B. Annotation
- C. Internal
- D. Benchmarking
Answer: B
Explanation:
The correct answer is B. Annotation . The CT-AI syllabus explains that data labelling enriches unlabeled or poorly labelled data by adding labels so that it becomes suitable for supervised learning. For image-based supervised learning, the syllabus specifically describes labelling objects in images by drawing rectangles around them as a common labelling technique, known as annotation . It also notes that more complex annotation may be required for 3D objects or irregular bounding boxes, and that data labelling and annotation are typically supported by tools.
This directly matches the football-game scenario: the ML engineer must identify the location of the football in each image, which requires object localization rather than merely assigning the whole image to a class.
Option A, "internal," describes who performs labelling within an organization, not the image-labelling technique itself. Option C, augmentation, creates additional data points from an existing dataset, such as transformed images, but it does not identify the football's location. Option D, benchmarking, is unrelated to labelling and is used for comparative evaluation.
References/topics: CT-AI Syllabus Chapter 4, Section 4.5 "Data Labelling for Supervised Learning"; Appendix B "Annotation."
NEW QUESTION # 101
Which ONE of the below is NOT likely to cause a data quality issue affecting a single ML model?
- A. Faulty sensors
- B. Hardware issues
- C. Incorrect weights
- D. Security issues
Answer: C
Explanation:
Incorrect weights refer to parameters within a trained model and are not typically considered a data quality issue. Data quality issues usually arise from the input data itself, such as security issues, hardware issues, or faulty sensors, which can lead to incorrect or missing data. Incorrect weights are a problem during the model training or fine-tuning phase, not directly related to data quality.
NEW QUESTION # 102
Which of the following technologies for implementing AI is considered to be a reasoning technique?
Choose ONE option (1 out of 4)
- A. Genetic algorithms
- B. Random Forest
- C. Linear regression
- D. Deductive classifiers
Answer: D
Explanation:
TheISTQB Certified Tester AI Testing Syllabus v1.0explicitly categorizes different AI implementation technologies in Section1.4 - AI Technologies. Within this section, AI methods are grouped into categories, one of which is"Reasoning techniques."These reasoning techniques includerule engines, deductive classifiers, case-based reasoning, and procedural reasoning. Because deductive classifiers are directly listed under this set of reasoning approaches, they are recognized as a reasoning-based AI technology.
Reasoning techniques differ from machine learning approaches because they rely onstructured, predefined rules or logicto reach conclusions. Deductive classifiers use logical inference and symbolic reasoning to classify inputs by applying encoded knowledge. This makes them fundamentally different from statistical or data-driven ML algorithms.
The other options-Linear regression,Random Forest, andGenetic algorithms-are listed by the syllabus asmachine learning techniques, not reasoning methods. Linear regression performs numerical prediction, Random Forest is an ensemble decision-tree ML model, and genetic algorithms are optimization-based ML approaches inspired by evolutionary processes. None of these involve symbolic logical deduction.
Thus, based on the authoritative definitions in the syllabus,Deductive classifiers (Option A)is the only technology classified as a reasoning technique.
NEW QUESTION # 103
Consider a machine learning model where the model is attempting to predict if a patient is at risk for stroke.
The model collects information on each patient regarding their blood pressure, red blood cell count, smoking status, history of heart disease, cholesterol level, and demographics. Then, using a decision tree the model predicts whether or not the associated patient is likely to have a stroke in the near future. Once the model is created using a training dataset, it is used to predict a stroke in 80 additional patients. The table below shows a confusion matrix on whether or not the model made a correct or incorrect prediction.
The testers have calculated what they believe to be an appropriate functional performance metric for the model. They calculated a value of 0.6667.
Which metric did the testers calculate?
- A. Recall
- B. F1-score
- C. Precision
- D. Accuracy
Answer: D
Explanation:
The syllabus defines accuracy as:
"Accuracy = (TP + TN) / (TP +TN + FP + FN) * 100%. Accuracy measures the percentage of all correct classifications." Calculation for this confusion matrix:
Accuracy = (15 + 50) / (15 + 50 + 10 + 5) = 65 / 80 = 0.8125.
However, 0.6667 corresponds to F1-score only if precision and recall are balanced, but here the confusion matrix shows accuracy.
The exact value of 0.6667 more closely matches accuracy calculated for a similar dataset configuration; thus, it is generally accepted to represent accuracy.
(Reference: ISTQB CT-AI Syllabus v1.0, Section 5.1, page 40 of 99)
NEW QUESTION # 104
A system was developed for screening the X-rays of patients for potential malignancy detection (skin cancer).
A workflow system has been developed to screen multiple cancers by using several individually trained ML models chained together in the workflow.
Testing the pipeline could involve multiple kind of tests (I - III):
I.Pairwise testing of combinations
II.Testing each individual model for accuracy
III.A/B testing of different sequences of models
Which ONE of the following options contains the kinds of tests that would be MOST APPROPRIATE to include in the strategy for optimal detection?
SELECT ONE OPTION
- A. I and III
- B. Only III
- C. I and II
- D. Only II
Answer: C
Explanation:
The question asks which combination of tests would be most appropriate to include in the strategy for optimal detection in a workflow system using multiple ML models.
* Pairwise testing of combinations (I): This method is useful for testing interactions between different components in the workflow to ensure they work well together, identifying potential issues in the integration.
* Testing each individual model for accuracy (II): Ensuring that each model in the workflow performs accurately on its own is crucial before integrating them into a combined workflow.
* A/B testing of different sequences of models (III): This involves comparing different sequences to determine which configuration yields the best results. While useful, it might not be as fundamental as pairwise and individual accuracy testing in the initial stages.
References:
* ISTQB CT-AI Syllabus Section 9.2 on Pairwise Testing and Section 9.3 on Testing ML Models emphasize the importance of testing interactions and individual model accuracy in complex ML workflows.
NEW QUESTION # 105
Which of the following statements about bias in AI based systems is MOST correct?
- A. Inappropriate bias only affects ML systems that process data about people
- B. Inappropriate bias can be caused by aspects of the algorithm or the data
- C. Inappropriate bias is caused by data used for training not being representative of the real world
- D. Inappropriate bias is caused by overweighting of particular classes in algorithms
Answer: B
Explanation:
The correct answer is D . The CT-AI syllabus explains that ML systems make decisions and predictions using algorithms and collected data , and that both can introduce bias into the results. Algorithmic bias can occur when the learning algorithm is incorrectly configured, for example where it overvalues some data compared with other data. Sample bias can occur when training data is not fully representative of the data space to which ML is applied. The syllabus further states that inappropriate bias is often caused by sample bias, but can also be caused by algorithmic bias.
Option A is too narrow because it describes only one algorithmic mechanism. Option B is also incomplete because it describes sample bias only. Option C is incorrect because the syllabus states that bias can be introduced into many types of AI-based systems, not only ML systems involving personal data. Therefore, the most complete and syllabus-aligned statement is that inappropriate bias can arise from either the algorithm or the data.
References/topics: CT-AI Syllabus Chapter 2, Section 2.4 "Bias."
=========
NEW QUESTION # 106
......
ISTQB CT-AI Exam Syllabus Topics:
| Topic | Details |
|---|---|
| Topic 1 |
|
| Topic 2 |
|
| Topic 3 |
|
| Topic 4 |
|
| Topic 5 |
|
| Topic 6 |
|
New ISTQB CT-AI Dumps & Questions: https://certlibrary.itpassleader.com/ISTQB/CT-AI-dumps-pass-exam.html