CertNexus Certified Artificial Intelligence Practitioner (CAIP) 認定 AIP-210 試験問題 (Q34-Q39):質問 # 34
In general, models that perform their tasks:
A. More accurately are less robust against adversarial attacks.
B. More accurately are neither more nor less robust against adversarial attacks.
C. Less accurately are less robust against adversarial attacks.
D. Less accurately are neither more nor less robust against adversarial attacks.
正解：A
解説：
Explanation
Adversarial attacks are malicious attempts to fool or manipulate machine learning models by adding small perturbations to the input data that are imperceptible to humans but can cause significant changes in the model output. In general, models that perform their tasks more accurately are less robust against adversarial attacks, because they tend to have higher confidence in their predictions and are more sensitive to small changes in the input data. References: [Adversarial machine learning - Wikipedia], [Why Are Machine Learning Models Susceptible to Adversarial Attacks? | by Anirudh Jain | Towards Data Science]
質問 # 35
Which of the following pieces of AI technology provides the ability to create fake videos?
A. Long short-term memory (LSTM) networks
B. Support-vector machines (SVM)
C. Generative adversarial networks (GAN)
D. Recurrent neural networks (RNN)
正解：C
解説：
Explanation
Generative adversarial networks (GAN) are a type of AI technology that can create fake videos, images, audio, or text that are realistic and indistinguishable from real ones. GAN consist of two neural networks: a generator and a discriminator. The generator tries to produce fake samples from random noise, while the discriminator tries to distinguish between real and fake samples. The two networks compete against each other in a game-like scenario, where the generator tries to fool the discriminator and the discriminator tries to catch the generator. Through this process, both networks improve their abilities until they reach an equilibrium where the generator can produce convincing fakes.
質問 # 36
Why do data skews happen in the ML pipeline?
A. Test and evaluation data are designed incorrectly.
B. There Is a mismatch between live input data and offline data.
C. There is a mismatch between live output data and offline data.
D. There is insufficient training data for evaluation.
正解：B
解説：
Explanation
Data skews happen in the ML pipeline when the distribution or characteristics of the live input data differ from those of the offline data used for training and testing the model. This can lead to a degradation of the model performance and accuracy, as the model is not able to generalize well to new data. Data skews can be caused by various factors, such as changes in user behavior, data collection methods, data quality issues, or external events. References: What is training-serving skew in Machine Learning?, Data preprocessing for ML: options and recommendations
質問 # 37
For each of the last 10 years, your team has been collecting data from a group of subjects, including their age and numerous biomarkers collected from blood samples. You are tasked with creating a prediction model of age using the biomarkers as input. You start by performing a linear regression using all of the data over the 10- year period, with age as the dependent variable and the biomarkers as predictors.
Which assumption of linear regression is being violated?
A. Independence
B. Normality
C. Linearity
D. Equality of variance (Homoscedastidty)
正解：A
解説：
Independence is an assumption of linear regression that states that the errors (residuals) of the model are independent of each other, meaning that they are not correlated or influenced by previous or subsequent errors. Independence can be violated when the data has serial correlation or autocorrelation, which means that the value of a variable at a given time depends on its previous or future values. This can happen when the data is collected over time (time series) or over space (spatial data). In this case, the data is collected over time from a group of subjects, which may introduce serial correlation among the errors.
質問 # 38
Which of the following tests should be performed at the production level before deploying a newly retrained model?
A. Security test
B. A/Btest
C. Unit test
D. Performance test
正解：D
解説：
Explanation
Performance testing is a type of testing that should be performed at the production level before deploying a newly retrained model. Performance testing measures how well the model meets the non-functional requirements, such as speed, scalability, reliability, availability, and resource consumption. Performance testing can help identify any bottlenecks or issues that may affect the user experience or satisfaction with the model. References: [Performance Testing Tutorial: What is, Types, Metrics & Example], [Performance Testing for Machine Learning Systems | by David Talby | Towards Data Science]