WorksheetsIntroduction to AI and Azure Custom Vision
Total questions: 10
Worksheet time: 5mins
Which of the following results does an object detection model typically return for an image?
A class label and probability score for the image
Bounding box coordinates that indicates the region of the image where all of the objects it contains are located
A class label, probability, and bounding box for each object in the image
The sea-level rise, the chances of a forest fire, or how many people will be born in a given year can be predicted using?
Regression
Classification
Anomaly
Reinforcement learning
Deep learning is a _______________of ML.
Superset
Intersection
Union
Subset
What does the mAP score tell you?
If a tag is predicted by your model how likely is it to be right?
Out of tags that the model should predict how many did it find correctly.
The overall object detector performance
Minimum overlap to be considered before it is considered a correct prediction
You want to use the Computer Vision service to identify the location of individual items in an image. Which of the following features should you retrieve?
objects
tags
categories
You train an image classification model that achieves less than satisfactory evaluation metrics. How might you improve it?
Reduce the size of the images used to train the model.
Add a new label for "unknown" classes.
Add more images to the training set.
You have published an image classification model. What information must you provide to developers who want to use it?
Only the project ID.
The project ID, the model name, and the key and endpoint for the prediction resource
The project ID, iteration number, and the key and endpoint for the training resource.
How to improve accuracy?
Increase the number of same kind of images
Increase the number of diverse Images
Decrease the number of diverse images
There is no way to improve accuracy after training
Your organization has a payment gateway, and you see there is some unusual transaction. Which service you can use to detect such transaction.
Machine Learning
Classification
Anamoly Detection
Sentiment Analysis
You want to create an application in which you have to process your own photos. which services you will use?
Computer Vision
Custom Vision
OCR
Photo Analysis
