Exam AI-900 topic 1 question 70 discussion

C is correct. Anomaly detection is unsupervised learning that detect "deviation" from norm. To correctly identify the "correct" plastic bottle, computer vision should be used.

answer is correct

Computer Vision

C is the answer. https://learn.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/overview Azure 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 visual characteristics. Each label represents a classification or object. Unlike the Computer Vision service, Custom Vision allows you to specify your own labels and train custom models to detect them.

Computer vision focuses on teaching machines to interpret and understand visual information from images or videos. In this case, the recycling machine needs to analyze the shape of items to determine whether they are bottles or not. By using computer vision techniques, such as image classification or object detection, the machine can process visual inputs and accurately identify bottles based on their shape. Anomaly detection, conversational AI, and natural language processing are not directly applicable to this scenario: Anomaly detection is used to identify rare or unusual patterns or outliers in data, which is not the primary requirement for the recycling machine. Conversational AI involves building conversational agents or chatbots to interact with users using natural language, which is not the main objective of the recycling machine. Natural language processing focuses on processing and understanding human language, which is not directly relevant for identifying bottles based on their shape.

Computer vision makes it possible to detect the shape and then avoid those that do not fit.

C is corrct

Correct. It was there in 8.5.2023 exam

I think the words 'reject all items' is included in the question just to confuse us. The use-case here is to identify correct shaped bottle AND then recycle them in the machine. What happens to the rest of bottles is immaterial, not part of the design of the machine. If the use-case was 'throw out bottles which are not of specified shape', then it becomes a Anomaly detection task. Even then, to train on specific shape, Custom vision service is required. So, of the options available, computer vision is the correct service.

Answer is correct

computer vision allows for the automatic exclusion of odd-shaped bottles. anomaly detection is meant for suspicious activities

Object detection under Computer Vision

C is correct

computer vision is correct

Maybe you need at least Custom vision + Anomaly. Deviations of the size is anomaly thus Anomaly detection, but you need Vision for input perhaps?

C. Computer Vision is the best answer here, but it should be Custom Vision. The documentation of Anomaly Detection never mentions images or vision, only time-series data as input. https://docs.microsoft.com/en-au/azure/cognitive-services/anomaly-detector/overview Maybe, at the actual exam, the option is Custom Vision instead of Computer Vision. Can someone confirm or deny this assumption?

The key here is "shape" not "sizes". Agree with the comments on custom vision, however since it is not listed among the options, the correct answer is computer vision. Granted at first glance, it is tempting to select anomaly detection and it is understandable.