Microsoft Microsoft Certifications AI-900 Questions & Answers

• Question 111:

  You have an AI-based loan approval system.

  During testing, you discover that the system has a gender bias.

  Which responsible Al principle does this violate?

  A. accountability

  B. reliability and safety

  C. transparency

  D. fairness

  Correct Answer: D

  Fairness - AI systems should treat all people fairly

  Incorrect: Accountability - People should be accountable for AI systems Reliability and Safety - AI systems should perform reliably and safely Transparency - AI systems should be understandable

  Reference: https://dataninja.medium.com/6-principles-of-responsible-ai-b90f745b73dc

• Question 112:

  In a machine learning model, the data that is used as inputs are called ________.

  Select the answer that correctly completes the sentence.

  A. dataset

  B. labels

  C. variables

  Correct Answer: B

  In machine learning, data labeling is the process of identifying raw data (images, text files, videos, etc.) and adding one or more meaningful and informative labels to provide context so that a machine learning model can learn from it.

  Reference: https://docs.microsoft.com/en-us/azure/machine-learning/how-to-create-image-labeling-projects

• Question 113:

  You are developing a system to predict the prices of insurance for drivers in the United Kingdom.

  You need to minimize bias in the system.

  What should you do?

  A. Remove information about protected characteristics from the data before sampling.

  B. Take a training sample that is representative of the population in the United Kingdom.

  C. Create a training dataset that uses data from global insurers.

  D. Take a completely random training sample.

  Correct Answer: C

  Best practices you implement Use more data Using more data is the simplest and best possible way to prevent overfitting, and as an added bonus typically increases accuracy. When you use more data, it becomes harder for the model to memorize exact patterns, and it is forced to reach solutions that are more flexible to accommodate more conditions. It's also important to recognize statistical bias, to ensure your training data doesn't include isolated patterns that won't exist in live-prediction data. This scenario can be difficult to solve, because there may not be overfitting between your train and test sets, but there may be overfitting present when compared to live test data.

  Note: Prevent overfitting and imbalanced data with automated machine learning The best way to prevent overfitting is to follow ML best-practices including:

  -> Using more training data, and eliminating statistical bias Preventing target leakage Using fewer features Regularization and hyperparameter optimization Model complexity limitations Cross-validation

  Reference: https://learn.microsoft.com/en-us/azure/machine-learning/concept-manage-ml-pitfalls

• Question 114:

  Which statement is an example of a Microsoft responsible AI principle?

  A. AI systems must use only publicly available data

  B. AI systems must be transparent and inclusive

  C. AI systems must keep personal details public

  D. AI systems must protect the interests of the company

  Correct Answer: B

• Question 115:

  Predicting how many vehicles will travel across a bridge on a give day is an example of _______. Select the answer that correctly completes the sentence.

  A. regression

  B. translation

  C. classification

  D. clustering

  Correct Answer: A

  Regression is a supervised machine learning technique used to predict numeric values.

  Reference: https://docs.microsoft.com/en-us/learn/modules/create-regression-model-azure-machine-learning-designer/

• Question 116:

  You have a dataset.

  You need to build an Azure Machine Learning classification model that will identify defective products.

  What should you do first?

  A. Load the dataset.

  B. Create a clustering model.

  C. Split the data into training and testing datasets.

  D. Create a classification model.

  Correct Answer: C

  Understand steps for classification

  You can think of the steps to train and evaluate a classification machine learning model as:

  1.

  Prepare data: Identify the features and label in a dataset. Pre-process, or clean and transform, the data as needed.

  2.

  Train model: Split the data into two groups, a training and a validation set. Train a machine learning model using the training data set. Test the machine learning model for performance using the validation data set.

  3.

  Evaluate performance: Compare how close the model's predictions are to the known labels.

  4.

  Deploy a predictive service: After you train a machine learning model, you need to convert the training pipeline into a real-time inference pipeline. Then you can deploy the model as an application on a server or device so that others can use it.

  Reference: https://docs.microsoft.com/en-us/learn/modules/create-classification-model-azure-machine-learning-designer/classification-steps

• Question 117:

  You need to develop a mobile app for employees to scan and store their expenses while travelling. Which type of computer vision should you use?

  A. face detection

  B. image classification

  C. object detection

  D. optical character recognition (OCR)

  Correct Answer: D

  You can use OCR to Turn PDF and Image Files into Electronic Documents.

  Reference: https://learn.microsoft.com/en-us/dynamics-nav-app/across-how-use-ocr-pdf-images-files

• Question 118:

  You need to make the written press releases of your company available in a range of languages. Which service should you use?

  A. Speech

  B. Language

  C. Translator

  D. Personalizer

  Correct Answer: C

  Translator, an AI service for real-time document and text translation.

  Translate text instantly or in batches across more than 100 languages, powered by the latest innovations in machine translation. Support a wide range of use cases, such as translation for call centers, multilingual conversational agents, or inapp communication.

  Reference: https://azure.microsoft.com/en-us/services/cognitive-services/translator/4

• Question 119:

  An app that analyzes social media posts to identify their tone is an example of which type of natural language processing (NLP) workload?

  A. sentiment analysis

  B. speech recognition

  C. key phrase extraction

  D. entity recognition

  Correct Answer: A

  Sentiment analysis is analytical technique that uses statistics, natural language processing, and machine learning to determine the emotional meaning of communications. Companies use sentiment analysis to evaluate customer messages, call center interactions, online reviews, social media posts, and other content.

  Reference: https://www.cio.com/article/189218/what-is-sentiment-analysis-using-nlp-and-ml-to-extract-meaning.html

• Question 120:

  A historian can use ________ to digitize newspaper articles. Select the answer that correctly completes the sentence.

  A. Object detection

  B. Facial recognition

  C. Image classification

  D. Optical character recognition (OCR)

  Correct Answer: D