exam questions

Exam AI-100 All Questions

View all questions & answers for the AI-100 exam

Exam AI-100 topic 2 question 16 discussion

Actual exam question from Microsoft's AI-100
Question #: 16
Topic #: 2
[All AI-100 Questions]

You plan to perform analytics of the medical records of patients located around the world.
You need to recommend a solution that avoids storing and processing data in the cloud.
What should you include in the recommendation?

  • A. Azure Machine Learning Studio
  • B. the Text Analytics API that has container support
  • C. Azure Machine Learning services
  • D. an Apache Spark cluster that uses MMLSpark
Show Suggested Answer Hide Answer
Suggested Answer: D 🗳️
The Microsoft Machine Learning Library for Apache Spark (MMLSpark) assists in provisioning scalable machine learning models for large datasets, especially for building deep learning problems. MMLSpark works with SparkML pipelines, including Microsoft CNTK and the OpenCV library, which provide end-to-end support for the ingress and processing of image input data, categorization of images, and text analytics using pre-trained deep learning algorithms.
References:
https://subscription.packtpub.com/book/big_data_and_business_intelligence/9781789131956/10/ch10lvl1sec61/an-overview-of-the-microsoft-machine-learning- library-for-apache-spark-mmlspark

Comments

Chosen Answer:
This is a voting comment (?). It is better to Upvote an existing comment if you don't have anything to add.
Switch to a voting comment New
lrnr
Highly Voted 5 years, 5 months ago
B) should be the correct answer here
upvoted 13 times
K7P
5 years, 4 months ago
I agree. Containers can help store data locally without being stored on Cloud.
upvoted 3 times
...
ZainZaidi
5 years, 3 months ago
Spark cluster will be deployed using HDInsight or used with Databricks and clusters cant be deployed locally therefore all processing and storing will be on cloud. D can't be right answer.
upvoted 2 times
princesskay
5 years, 1 month ago
you can deploy a cluster locally: https://medium.com/@joseignaciocastelli92/how-to-make-your-first-local-cluster-with-kubernetes-e15fc4b262e7
upvoted 1 times
...
...
KNG
4 years, 2 months ago
Shoud be B, https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to-install-containers?tabs=sentiment
upvoted 1 times
...
allanm
4 years ago
Correct. Anytime you get a question that suggests wording like "should not be uploaded to the cloud" usually suggests deploying a container service. Since text analytics can help perform analytics on medical documents, B is the right answer.
upvoted 1 times
...
...
Mfweuydg
Highly Voted 5 years, 2 months ago
D is correct. B is not correct as the text analytics API can't make analytics for medical records it's used in sentiment analysis, key phrase extraction, and language detection. https://github.com/Azure/mmlspark
upvoted 13 times
jorama
5 years ago
The question gives you two key pieces of information regarding the solution: 1 - Analytics on medical records (vague statement) scattered all over the world; 2 - The data must not be stored nor processed in the cloud; The only relevant example in the link you referenced is example 8, which deals with....**drum roll** key phrase extraction, which you also state that Text Analytics API performs. Therefore, Text Analytics API seems like the right choice for me, as it addresses all the requirements of the question.
upvoted 4 times
giusecozza
5 years ago
MMLSpark can be deployed locally via Docker container and it uses Microsoft Cognitive Services to "tackle problems in Deep Learning, Micro-Service Orchestration, Gradient Boosting, Model Interpretability, and other areas of modern computation". If you want to make analytics on data you need an environment (while Text Analytics may represent only a piece of the solution), and Spark would be a good choice. So, in my opinion D is correct. Just check out here: https://mmlspark.blob.core.windows.net/website/index.html
upvoted 7 times
...
...
...
rveney
Most Recent 1 year, 12 months ago
the most suitable recommendation for avoiding storing and processing data in the cloud is to use the Text Analytics API with container support (Option B).
upvoted 1 times
...
Cornholioz
4 years, 4 months ago
"Medical Records" most likely contain images. Text Analytics is "text" analytics. Azure Machine Learning works on an Edge Node... more seamlessly too, and is native to Azure. But I think bulk of the data would still need to get stored on the Cloud. Eliminating this option. MML Spark does run on Edge. But can it store all the date locally? I think AML is a better option here because it can work off of local data. https://docs.microsoft.com/en-us/azure/architecture/hybrid/deploy-ai-ml-azure-stack-edge That said, I still don't have a strong opinion about the answer unfortunately.
upvoted 1 times
...
htest2000
4 years, 8 months ago
B) is correct answer to me. This allows to store data locally. In addition, Text Analytics for Health can be used for medical record processing.
upvoted 5 times
...
varga123akos
4 years, 10 months ago
Though Text Analytics for health is in preview, but the use case on this link is an answer for this question: https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/how-tos/text-analytics-for-health
upvoted 2 times
deenson
4 years, 2 months ago
You never use something in Preview in production environment.
upvoted 1 times
...
...
Community vote distribution
A (35%)
C (25%)
B (20%)
Other
Most Voted
A voting comment increases the vote count for the chosen answer by one.

Upvoting a comment with a selected answer will also increase the vote count towards that answer by one. So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.

SaveCancel
Loading ...