AI 900 questions

Language service

Used for understanding and analyzing text and creating intelligent applications

Natural language processing

Used to understand and analyze text and create intelligent applications

Which scenario is an example of a webchat bot?

From a website interface, answer common questions about schedule events and ticket purchases for a music festival

The INTERACTIVE answering of questions entered by a user as part of an application is an example of

Conversational AI

What are three Microsoft guiding principles for responsible AI?

- Reliability and safety - Inclusiveness - Fairness

What are two tasks that can be performed by using the computer vision service?

- detect faces in an image - recognize handwritten text

Fairness

A core ethical principle that all humans aim to understand and apply. This principle is even more important when AI systems are being developed. Key checks and balances need to make sure that the system's decisions don't discriminate or run a gender, race, sexual orientation, or religion bias toward a group or individual

Clustering

A method of grouping data points into similar clusters. Also called segmentation Example: you might apply clustering to find similar people by demographics

A company employs a team of customers service agents to provide telephone and email support to customers. The company develops a webchat bot to provide automated answers to common customer queries. Which business benefit should the company expect as a result of creating the webchat bot solution?

A reduce workload for the customer service agents

Complete the sentence by choosing appropriate option in the answer area Azure machine learning designer lets you create machine learning models by:

Adding and connecting modules on a visual canvas

Speech text

Analyzes audio in real-time or batch to transcribe the spoken word into text Out of the box, speech to text utilizes a Universal Language Model as a base model that is trained with Microsoft-owned data and reflects commonly used spoken language

You want to create a model to predict sales of ice cream based on historic data that includes daily ice cream sales total and weather measurements. Which Azure service should you use?

Azure Machine Learning Enables you to train a predictive model from existing data

Which of the following is the calculated probability of a correct image classification A. Accuracy B. Confidence C. Root mean square Error D. Sentiment

B

A bank wants to use historic credit card repayment records to categorize credit card applications as low-risk or high based on characteristics like the credit amount, the income of the borrower, and the credit period. What kind of machine learning model should the bank use automated machine learning to create?

Classification

Learning type: predict whether a student will complete a university course

Classification

Learning type: segment customers into different groups to support a marketing department

Clustering

You are designing an AI application that uses images to detect cracks in window-panes of buildings and warns when a window-pane should be repaired or replaced. What AI workload is described?

Computer vision

You use Azure Machine Learning designer to create a training pipeline for a classification model. What must you do before deploying the model as a service?

Create an inference pipeline from the training pipeline

Which following service should you use to train an object detection model by using OWN images

Custom vision

You build a machine learning model by using the automate machine learning user interface (UI). You need to ensure that the model meets the Microsoft transparency principle for responsible AI. What should you do?

Enable explain best model (ML 'Black box') Most business run on trust and being able to open the ML box. This helps build transparency and trust. In heavily regulated industries like healthcare and banking, it is critical to comply with regulations and best practices. One key aspect of this understanding the relationship between input variables (features) and model output. Knowing both the magnitude and direction of the impact each feature (feature importance) has on the predicted value helps better understand and explain the model. With model explain ability, we enable you to understand feature importance as part of automated ML runs

Ensuring that numeric variable in training data are in a similar scale is an example of ____

Feature selection

You can use QnA Maker to query an Azure SQL database. Y or N

N

Explainability

Helps data scientists, auditors, and business decision makers to ensure that AI systems can reasonably justify their decisions and how they reach their conclusions. This also ensures compliance with company policies industry standards and government regulations. A data scientist should be able to explain to the stakeholder how they achieved certain levels of accuracy and what influenced this outcome

Your company is exploring the use of voice recognition technologies in its smart home devices. The company wants to identify any barriers that might UNINTENTIONALLY leave out specific user groups. This an example of which Microsoft guiding principle for responsible AI?

Inclusiveness

Language understanding (LUIS)

Is a cloud based conversational AI service that applies custom machine-learning intelligence to a user's conversational, natural language text to predict overall meaning, and pull out relevant l, detailed information

Azure machine learning designer

Is a drag and drop interface used to train and deploy models in Azure Machine Learning

stratified random sampling

Is a method of sampling that involves the division of a population into smaller sub-groups known as strata

Transparency

Is about fully communicating the purpose of the system, how it works, and what limitations may be expected

Custom vision

Is an image recognition service that lets you build, deploy, and improve your own image identifier models An image identifier applies labels to images, according to their detected visual characteristics. Each label represents a classification or object

Split data model

Is particularly useful when you need to separate data into training and testing sets. Use the Split Rows option if you want to divide the data into two parts. You can specify the percentage of data to put in each split, but by default, the data is divided 50-50. You can also randomize the selection of rows in each group and use stratified sampling

Text analytics

Is used for deeper insights, like identifying a pattern or trend from the unstructured text Example: can be used to understand a negative spike in customer experience or popularity of a product

Anomaly detection

Is used to analyze data over time and identify unusual changes

Webchat bot

Just for answering common customer queries Can most surely reduce workload for the customer service agent

Inclusiveness

Mandates AI should consider all human races and experiences, and inclusive design practices can help developers to understand and address potential barriers that could unintentionally exclude people. Where possible, speech-to-text, text-to-speech, and visual recognition technology should be used to empower people with hearing, visual, and other impairments

The QnA Maker service can determine the intent of a user utterance. Y or N

N

You are creating a training pipeline for a regression model. You use a dataset that has multiple numeric columns in which the values are on different scales. You want to transform the numeric columns so that the values are all on a similar scale. You also want the transformation to scale relative to the minimum and maximum values in each column. Which module should you add to the pipeline?

Normalize data

Returning a bounding box that indicates the location of a vehicle in an image is an example of

Object detection

You need to determine the location of cars in an image so that you can estimate the distance between the cars. Which type of computer vision should you use?

Object detection

Computer vision services

Optical character recognition (OCR): extract printed and handwritten text from photos and documents. A deep-based model and works with text such as business documents, invoices, receipts, posters, business cards letters, and whiteboards Image Analysis: extracts many visual features from images, such as objects, faces, adult content, and auto-generated text descriptions Spatial analysis: the presence and movement of people of people on video feed and produces events that other systems can respond to.

Azure bot service

Provides a platform for conversational AI

Which AI service you use to create a bot from a frequently asked question (FAQ) document

QnA Maker Is a cloud based Natural Language Processing (NLP) service that allows you to create a natural conversational layer over your data. It is used to find the most appropriate answer for any input from your custome knowledge base (kb) of information

For a machine learning process, how should you split data from training and evaluation?

Randomly split the data into rows for training and rows for evaluation

Regression

Refers to prediction of a numeric target Linear regression attempts to establish a linear relationship between one or more independent variables and a numeric outcome, or dependent variable. You use this model to define a linear regression method, and then train a model using a labeled dataset. The trained model can then be used to make predictions

Learning type: predict how many minutes late a flight will arrive based on the amount of snowfall at an airport

Regression

Predicting how MANY HOURS of overtime a delivery person will work based on the number of order received is an example of

Regression

A housing dealership wants to use historic apartment sales data to train a machine learning model. The model should predict the PRICE of a pre-owned apartment based on its location, size and apartment aging. What kind of machine learning model should the dealership use automated machine learning to create?

Regression Anytime predicting a numeric value

Ensuring an AI system does not provide a prediction when important fields contain unusual or missing values is ******* principle for responsible AI.

Reliability and safety

You want to use automated machine learning to train a regression model with the best possible R2 score. How should you configure the automated machine learning experiment?

Set the Primary metric to R2 score The primary metric determines the metric used to evaluate the performing model

Feature engineering

The process of creating new features from raw data to increase the predictive power of the learning algorithm

Feature selection

The process of selecting the key subset of features to reduce the dimensionality of the training problem

Classification

Two class classification provides the answer to simple two-choice questions such as Yes/No or True/False

You should use QnA Maker when you want a knowledge base to provide the same answer to different users who submit similar questions. Y or N

Y

____ is used to generate additional features

feature engineering

A predictive app provides audio output for visually impaired users. Which principle of Responsible AI is reflected here?

inclusiveness