Exam DP-100 topic 1 question 32 discussion

Actual exam question from Microsoft's DP-100

Question #: 32
Topic #: 1

This question is included in a number of questions that depicts the identical set-up. However, every question has a distinctive result. Establish if the recommendation satisfies the requirements.
You have been tasked with constructing a machine learning model that translates language text into a different language text.
The machine learning model must be constructed and trained to learn the sequence of the.
Recommendation: You make use of Convolutional Neural Networks (CNNs).
Will the requirements be satisfied?

A. Yes
B. No

Show Suggested Answer

Suggested Answer: B 🗳️

by Jultis at Aug. 17, 2021, 11:02 a.m.

Comments

Submit Cancel

Jultis

Highly Voted 2 years, 10 months ago

Use Reccurent Neural Network (RNN) for translations.

upvoted 12 times

...

james2033

Most Recent 8 months, 4 weeks ago

Selected Answer: B

Convolution Neural Networks (CNN) for training images machine learning model. Recurrent Neural Networks (RNN) for training text (words sequence) in term of seq2seq, but now it is out of date, use Transformer as alternative solution. Anyway, CNN is incorrect for NLP.

upvoted 2 times

james2033

8 months, 4 weeks ago

Transfer learning (Transformer architecture) for Machine translation https://learn.microsoft.com/en-us/azure/machine-learning/concept-deep-learning-vs-machine-learning?view=azureml-api-2#machine-translation .

upvoted 1 times

...

EmmettBrown

1 year, 2 months ago

Selected Answer: B

B is the answer

upvoted 1 times

...

eloyinaay

1 year, 4 months ago

The answer is correct RNN are for NLP and

upvoted 1 times

...

Arend78

1 year, 7 months ago

Selected Answer: B

https://www.techtarget.com/searchenterpriseai/feature/CNN-vs-RNN-How-they-differ-and-where-they-overlap "CNNs are preferred in interpreting visual data, sparse data or data that does not come in sequence," [...] "Recurrent neural networks, on the other hand, are designed to recognize sequential or temporal data. They do better predictions considering the order or sequence of the data as they relate to previous or the next data nodes."

upvoted 4 times

...

ranjsi01

2 years, 5 months ago

cnn for image classification

upvoted 4 times

...