[2024年07月24日] あなたを合格させるAIP-210無料最新問題集でCertNexus練習テスト
無料でゲット！高評価CertNexus AIP-210試験問題集を今すぐダウンロード！
CertNexus AIP-210 認定試験の出題範囲：
| トピック | 出題範囲 |
|---|---|
| トピック 1 |
|
| トピック 2 |
|
| トピック 3 |
|
質問 # 20
A product manager is designing an Artificial Intelligence (AI) solution and wants to do so responsibly, evaluating both positive and negative outcomes.
The team creates a shared taxonomy of potential negative impacts and conducts an assessment along vectors such as severity, impact, frequency, and likelihood.
Which modeling technique does this team use?
- A. Process
- B. Harms
- C. Threat
- D. Business
正解：B
解説：
Explanation
Harms modeling is a technique that helps product managers design AI solutions responsibly by evaluating both positive and negative outcomes. Harms modeling involves creating a shared taxonomy of potential negative impacts and conducting an assessment along vectors such as severity, impact, frequency, and likelihood. Harms modeling can help identify and mitigate any risks or harms that may arise from using AI solutions. References: [Harms Modeling for Responsible AI | by Google Developers | Google Developers],
[Harms Modeling for Responsible AI - YouTube]
質問 # 21
Why do data skews happen in the ML pipeline?
- A. There Is a mismatch between live input data and offline data.
- B. There is a mismatch between live output data and offline data.
- C. Test and evaluation data are designed incorrectly.
- D. There is insufficient training data for evaluation.
正解：A
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 # 22
Which of the following unsupervised learning models can a bank use for fraud detection?
- A. k-means
- B. DB5CAN
- C. Anomaly detection
- D. Hierarchical clustering
正解：C
解説：
Explanation
Anomaly detection is an unsupervised learning technique that identifies outliers or abnormal patterns in data, which can be useful for fraud detection. Anomaly detection algorithms can learn the normal behavior of transactions and flag the ones that deviate significantly from the norm, indicating possible fraud.
質問 # 23
You are implementing a support-vector machine on your data, and a colleague suggests you use a polynomial kernel. In what situation might this help improve the prediction of your model?
- A. When it is necessary to save computational time.
- B. When there is high correlation among the features.
- C. When the categories of the dependent variable are not linearly separable.
- D. When the distribution of the dependent variable is Gaussian.
正解：C
解説：
Explanation
A support-vector machine (SVM) is a supervised learning algorithm that can be used for classification or regression problems. An SVM tries to find an optimal hyperplane that separates the data into different categories or classes. However, sometimes the data is not linearly separable, meaning there is no straight line or plane that can separate them. In such cases, a polynomial kernel can help improve the prediction of the SVM by transforming the data into a higher-dimensional space where it becomes linearly separable. A polynomial kernel is a function that computes the similarity between two data points using a polynomial function of their features.
質問 # 24
A big data architect needs to be cautious about personally identifiable information (PII) that may be captured with their new IoT system. What is the final stage of the Data Management Life Cycle, which the architect must complete in order to implement data privacy and security appropriately?
- A. Duplicate
- B. Detain
- C. De-Duplicate
- D. Destroy
正解：D
解説：
Explanation
The final stage of the data management life cycle is data destruction, which is the process of securely deleting or erasing data that is no longer needed or relevant for the organization. Data destruction ensures that data is disposed of in compliance with any legal or regulatory requirements, as well as any internal policies or standards. Data destruction also protects the organization from potential data breaches, leaks, or thefts that could compromise its privacy and security. Data destruction can be performed using various methods, such as overwriting, degaussing, shredding, or incinerating
質問 # 25
An AI practitioner incorporates risk considerations into a deployment plan and decides to log and store historical predictions for potential, future access requests.
Which ethical principle is this an example of?
- A. Transparency
- B. Privacy
- C. Fairness
- D. Safety
正解：A
解説：
Explanation
Transparency is an ethical principle that describes the degree to which an AI system can provide clear and understandable information about its inputs, outputs, processes, and decisions. Transparency can help increase trust and confidence among users and stakeholders, as well as enable accountability and responsibility for the system's actions and outcomes. Logging and storing historical predictions for potential, future access requests is an example of transparency, as it can help provide evidence and explanation for the system's recommendations, as well as facilitate auditing and feedback.
質問 # 26
Which of the following tools would you use to create a natural language processing application?
- A. DeepDream
- B. NLTK
- C. Azure Search
- D. AWS DeepRacer
正解：B
解説：
Explanation
NLTK (Natural Language Toolkit) is a Python library that provides a set of tools and resources for natural language processing (NLP). NLP is a branch of AI that deals with analyzing, understanding, and generating natural language texts or speech. NLTK offers modules for various NLP tasks, such as tokenization, stemming, lemmatization, parsing, tagging, chunking, sentiment analysis, named entity recognition, machine translation, text summarization, and more .
質問 # 27
Which of the following is a common negative side effect of not using regularization?
- A. Overfitting
- B. Low test accuracy
- C. Slow convergence time
- D. Higher compute resources
正解：A
解説：
Explanation
Overfitting is a common negative side effect of not using regularization. Regularization is a technique that reduces the complexity of a model by adding a penalty term to the loss function, which prevents the model from learning too many parameters that may fit the noise in the training data. Overfitting occurs when the model performs well on the training data but poorly on the test data or new data, because it has memorized the training data and cannot generalize well. References: Regularization (mathematics) - Wikipedia, Overfitting in Machine Learning: What It Is and How to Prevent It
質問 # 28
Your dependent variable Y is a count, ranging from 0 to infinity. Because Y is approximately log-normally distributed, you decide to log-transform the data prior to performing a linear regression.
What should you do before log-transforming Y?
- A. Explore the data for outliers.
- B. Subtract the mean of Y from all the Y values.
- C. Add 1 to all of the Y values.
- D. Divide all the Y values by the standard deviation of Y.
正解：C
解説：
Explanation
Before log-transforming Y, we should add 1 to all of the Y values. This is because log transformation is undefined for zero or negative values, and some of the Y values may be zero. Adding 1 to all of the Y values can avoid this problem and ensure that the log transformation is valid and meaningful. Adding 1 to all of the Y values is also known as a log-plus-one transformation.
質問 # 29
Below are three tables: Employees, Departments, and Directors.
Employee_Table
Department_Table
Director_Table
ID
Firstname
Lastname
Age
Salary
DeptJD
4566
Joey
Morin
62
$ 122,000
1
1230
Sam
Clarck
43
$ 95,670
2
9077
Lola
Russell
54
$ 165,700
3
1346
Lily
Cotton
46
$ 156,000
4
2088
Beckett
Good
52
$ 165,000
5
Which SQL query provides the Directors' Firstname, Lastname, the name of their departments, and the average employee's salary?
- A. SELECT m.Firstname, m.Lastname, d.Name, AVG(e.Salary) as Dept_avg_Salary FROM Employee_Table as e RIGHT JOIN Department_Table as d on e.Dept = d.Name INNER JOIN Directorjable as m on d.ID = m.DeptJD GROUP BY e.Salary
- B. SELECT m.Firstname, m.Lastname, d.Name, AVG(e.Salary) as Dept_avg_Salary FROM Employee_Table as e RIGHT JOIN Departmentjable as d on e.Dept = d.Name INNER JOIN Directorjable as m on d.ID = m.DeptJD GROUP BY d.Name
- C. SELECT m.Firstname, m.Lastname, d.Name, AVG(e.Salary) as Dept_avg_Salary FROM Employee_Table as e RIGHT JOIN Department_Table as d on e.Dept = d.Name INNER JOIN Directorjable as m on d.ID = m.DeptID GROUP BY m.Firstname, m.Lastname, d.Name
- D. SELECT m.Firstname, m.Lastname, d.Name, AVG(e.Saiary) as Dept_avg_Saiary FROM Employee_Table as e LEFT JOIN Department_Table as d on e.Dept = d.Name LEFT JOIN Directorjable as m on d.ID = m.DeptJD GROUP BY m.Firstname, m.Lastname, d.Name
正解：C
解説：
Explanation
This SQL query provides the Directors' Firstname, Lastname, the name of their departments, and the average employee's salary by joining the three tables using the appropriate join types and conditions. The RIGHT JOIN between Employee_Table and Department_Table ensures that all departments are included in the result, even if they have no employees. The INNER JOIN between Department_Table and Directorjable ensures that only departments with directors are included in the result. The GROUP BY clause groups the result by the directors' names and departments' names, and calculates the average salary for each group using the AVG function. References: SQL Joins - W3Schools, SQL GROUP BY Statement - W3Schools
質問 # 30
Which two encodes can be used to transform categories data into numerical features? (Select two.)
- A. Log Encoder
- B. One-Hot Encoder
- C. Count Encoder
- D. Mean Encoder
- E. Median Encoder
正解：B、D
解説：
Explanation
Encoding is a technique that transforms categorical data into numerical features that can be used by machine learning models. Categorical data are data that have a finite number of possible values or categories, such as gender, color, or country. Encoding can help convert categorical data into a format that is suitable and understandable for machine learning models. Some of the encoding methods that can be used to transform categorical data into numerical features are:
Mean Encoder: Mean encoder is a method that replaces each category with the mean value of the target variable for that category. Mean encoder can capture the relationship between the category and the target variable, but it may cause overfitting or multicollinearity problems.
One-Hot Encoder: One-hot encoder is a method that creates a binary vector for each category, where only one element has a value of 1 (the hot bit) and the rest have a value of 0. One-hot encoder can create distinct and orthogonal vectors for each category, but it may increase the dimensionality and sparsity of the data.
質問 # 31
You are developing a prediction model. Your team indicates they need an algorithm that is fast and requires low memory and low processing power. Assuming the following algorithms have similar accuracy on your data, which is most likely to be an ideal choice for the job?
- A. Random forest
- B. Deep learning neural network
- C. Ridge regression
- D. Support-vector machine
正解：C
解説：
Explanation
Ridge regression is a type of linear regression that adds a regularization term to the loss function to reduce overfitting and improve generalization. Ridge regression is fast and requires low memory and low processing power, as it only involves solving a system of linear equations. Ridge regression can also handle multicollinearity (high correlation among predictors) by shrinking the coefficients of correlated predictors.
質問 # 32
An AI system recommends New Year's resolutions. It has an ML pipeline without monitoring components.
What retraining strategy would be BEST for this pipeline?
- A. Periodically before New Year's Day and after New Year's Day
- B. When data drift is detected
- C. Periodically every year
- D. When concept drift is detected
正解：C
解説：
Explanation
Retraining is the process of updating an existing ML model with new or updated data to maintain or improve its performance and relevance. Retraining can help address various issues or challenges in ML systems, such as data drift, concept drift, model degradation, or changing requirements. Retraining can be done using different strategies, such as periodically, continuously, or on-demand.
For an AI system that recommends New Year's resolutions, retraining periodically every year would be the best strategy for this pipeline. This is because New Year's resolutions are seasonal and time-sensitive, meaning that they may vary depending on the year or the current situation. Retraining periodically every year can help ensure that the system's recommendations are up-to-date and relevant for each new year.
質問 # 33
For a particular classification problem, you are tasked with determining the best algorithm among SVM, random forest, K-nearest neighbors, and a deep neural network. Each of the algorithms has similar accuracy on your data. The stakeholders indicate that they need a model that can convey each feature's relative contribution to the model's accuracy. Which is the best algorithm for this use case?
- A. Random forest
- B. SVM
- C. K-nearest neighbors
- D. Deep neural network
正解：A
解説：
Explanation
Random forest is an ensemble learning method that combines multiple decision trees to create a more accurate and robust classifier or regressor. Random forest can convey each feature's relative contribution to the model's accuracy by measuring how much the prediction error increases when a feature is randomly permuted. This metric is called feature importance or Gini importance. Random forest can also provide insights into the interactions and dependencies among features by visualizing the decision trees .
質問 # 34
Which of the following is NOT a valid cross-validation method?
- A. Bootstrapping
- B. K-fold
- C. Leave-one-out
- D. Stratification
正解：D
解説：
Explanation
Stratification is not a valid cross-validation method, but a technique to ensure that each subset of data has the same proportion of classes or labels as the original data. Stratification can be used in conjunction with cross-validation methods such as k-fold or leave-one-out to preserve the class distribution and reduce bias or variance in the validation results. Bootstrapping, k-fold, and leave-one-out are all valid cross-validation methods that use different ways of splitting and resampling the data to estimate the performance of a machine learning model.
質問 # 35
When should you use semi-supervised learning? (Select two.)
- A. A small set of labeled data is biased toward one class.
- B. A small set of labeled data is available but not representative of the entire distribution.
- C. There is a large amount of unlabeled data to be used for predictions.
- D. There is a large amount of labeled data to be used for predictions.
- E. Labeling data is challenging and expensive.
正解：C、E
解説：
Explanation
Semi-supervised learning is a type of machine learning that uses both labeled and unlabeled data to train a model. Semi-supervised learning can be useful when:
Labeling data is challenging and expensive: Labeling data requires human intervention and domain expertise, which can be costly and time-consuming. Semi-supervised learning can leverage the large amount of unlabeled data that is easier and cheaper to obtain and use it to improve the model's performance.
There is a large amount of unlabeled data to be used for predictions: Unlabeled data can provide additional information and diversity to the model, which can help it learn more complex patterns and generalize better to new data. Semi-supervised learning can use various techniques, such as self-training, co-training, or generative models, to incorporate unlabeled data into the learning process.
質問 # 36
......
一発合格の秘訣は無料でゲット！AIP-210Certified 試験エンジンPDF：https://jp.fast2test.com/AIP-210-premium-file.html
AIP-210試験問題集合格には最新なテスト問題集：https://drive.google.com/open?id=15sGcmclI1nu1ODraiHYD3u8EV8Oq_Zce