ExamTopics Logo
Mail Us[email protected]
Menu
Amazon Discussions
exam questions

Exam AWS Certified Machine Learning - Specialty All Questions

View all questions & answers for the AWS Certified Machine Learning - Specialty exam
Go to Exam

Exam AWS Certified Machine Learning - Specialty topic 1 question 255 discussion

Exam question from Amazon's AWS Certified Machine Learning - Specialty
Question #: 255
Topic #: 1
[All AWS Certified Machine Learning - Specialty Questions]

A car company is developing a machine learning solution to detect whether a car is present in an image. The image dataset consists of one million images. Each image in the dataset is 200 pixels in height by 200 pixels in width. Each image is labeled as either having a car or not having a car.

Which architecture is MOST likely to produce a model that detects whether a car is present in an image with the highest accuracy?

  • A. Use a deep convolutional neural network (CNN) classifier with the images as input. Include a linear output layer that outputs the probability that an image contains a car.
  • B. Use a deep convolutional neural network (CNN) classifier with the images as input. Include a softmax output layer that outputs the probability that an image contains a car.
  • C. Use a deep multilayer perceptron (MLP) classifier with the images as input. Include a linear output layer that outputs the probability that an image contains a car.
  • D. Use a deep multilayer perceptron (MLP) classifier with the images as input. Include a softmax output layer that outputs the probability that an image contains a car.
Show Suggested Answer Hide Answer
Suggested Answer: B 🗳️
by SandeepGun at June 17, 2023, 4:30 p.m.
Disclaimers:
  • - ExamTopics website is not related to, affiliated with, endorsed or authorized by Amazon.
  • - Trademarks, certification & product names are used for reference only and belong to Amazon.

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
Submit Cancel
Carpediem78
2 months ago
Selected Answer: A
Softmax function used Multi-class Classification
upvoted 1 times
...
JonSno
5 months, 3 weeks ago
Answer B - B. Use a deep convolutional neural network (CNN) classifier with the images as input. Include a softmax output layer that outputs the probability that an image contains a car. This approach leverages the powerful feature extraction capabilities of CNNs and uses a softmax output layer, which is most suitable for binary classification tasks like detecting a car's presence.
upvoted 1 times
...
vkbajoria
7 months ago
Selected Answer: A
According to chat GPT it is A. when we say "linear output layer" in the context of binary classification, it might lead to confusion. The output itself for binary classification problems is not linear; instead, it's the result of applying a sigmoid function to a linear combination of features extracted by the neural network. The term "linear" might be more accurately replaced with "sigmoid activation" for the output neuron to reflect its role in producing a probability.
upvoted 2 times
JonSno
5 months, 3 weeks ago
Dont quite agree and Chat GPT not always perfect - https://ml4.me/a-deep-dive-into-convolutional-neural-network-architectures-with-tensorflow-in-sagemaker/
upvoted 3 times
...
...
loict
1 year, 1 month ago
Selected Answer: B
A. NO - linear output is not B. YES - CNN is good, softmax output is good C. NO - MLP is not good D. NO - MLP is not good
upvoted 3 times
...
goku58
1 year, 1 month ago
Selected Answer: B
Softmax is particularly useful when you want the network to make a clear choice among multiple classes. The question doesn't even ask for probabilities, it just asks for a binary classification. Ideally sigmoid activation function is used for binary classification, but when there is only 1 class, softmax will work the same way as sigmoid. The answer is still B, but just because linear layer is used for regression and not for binary classification. And of course, CNNs are better than MLP for image classifications.
upvoted 1 times
...
Mickey321
1 year, 2 months ago
Selected Answer: B
It is a wording puzzle. A should be right due to car or no car but in the answer it mentions probability. Hence, softmax is more appropriate despite it is not multi classification
upvoted 1 times
...
kaike_reis
1 year, 2 months ago
Selected Answer: B
For image classification problems we must use CNN, so we discard Letters C - D. Letter A is wrong, because linear output layer does not generate probability, but softmax. Letter B is correct.
upvoted 1 times
...
cfx210
1 year, 2 months ago
As it's a binary classification problem (car vs. no car) I would argue a linear output layer makes more sense than softmax...
upvoted 1 times
kaike_reis
1 year, 2 months ago
A linear layer will not generate a probability, so it's wrong my conrad.
upvoted 1 times
...
...
awsarchitect5
1 year, 3 months ago
Selected Answer: B
B is right
upvoted 1 times
...
SandeepGun
1 year, 4 months ago
Selected Answer: B
Both MLP and CNN can process images, but CNN is more accurate and can be used for more complex images
upvoted 2 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
exam
Someone Bought Contributor Access for:
SY0-701
London, 1 minute ago