최신ISTQB Certified Tester AI Testing - CT-AI무료샘플문제

A. Super AI

B. Conventional AI

C. Narrow AI

D. General AI

A. Metamorphic testing

B. Back-to-back testing

C. Adversarial testing

D. Pairwise testing

E. Exploratory data analysis

A. Creating and managing large amounts of test data can be difficult, especially when it needs to be representative

B. Using the same implementation for data acquisition by data scientists and testers prevents defect masking

C. Artificially generated data requires legal approval and must be sanitized and encrypted

D. The input data must always be the same over time, especially in real-world systems

A. Al-Assisted

B. Outsourced

C. Internal

D. Pre-labeled dataset

A. Cyclomatic complexity

B. Developers associated with previous code changes

C. Commit size

D. Lines of code changed

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

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

C. The model is too simplistic for the data

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

A. Sensitivity

B. Accuracy

C. -

D. F1 value

A. 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.

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

C. 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.

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

A. Value-change coverage

B. Neuron coverage

C. Threshold coverage

D. Sign-change coverage

A. Differences in data preparation steps between the training of the pre-trained model and consequent use of the model may result in reduced functional performance

B. The system may be vulnerable to adversarial attacks inherited from the pre trained model

C. The functional performance of the pre trained model could be lower than stakeholders expect

D. The functional performance of the system may exhibit bias

A. Explainability

B. Adaptability

C. Ethics

D. Inappropriate bias

A. A model for predicting academic performance was trained with data from students at one university.
The model shows low predictive accuracy when applied to other universities.

B. A model for the recognition of dogs was trained predominantly with pictures of dogs in parks. On pictures with other animals in parks, dogs are also falsely recognized.

C. A model for predicting IT system failures delivers too many false-negative predictions because the failures cannot be adequately explained via the log files used for training.

D. A previously trained model for recognizing cars is adapted and extended so that it can also identify the make of the car beyond its original function.

A. Explainability

B. Self-learning

C. Non-determinism

D. Autonomy