Which SageMaker Model is Best for Dog Breed Identification?
Question
You work as a machine learning specialist for a retail pet products chain.
Your company is trying to use machine learning to help determine the breed of dogs in the photos your customers tag on Instagram and Twitter.
You need to build a machine learning model to accomplish this problem. Which SageMaker model would you use to fit your machine learning problem best?
Answers
Explanations
Click on the arrows to vote for the correct answer
A. B. C. D.Answer: B.
Option A is incorrect.
K-Means is used to find discrete groupings in data.
It is mostly used on numeric data that is continuous.
Image data is not numeric and is not continuous, so K-Means would not be a good model for your dog image classification problem.
(See the Amazon SageMaker developer guide titled K-Means Algorithm)
Option B is correct.
The Image Classification model is used to solve classification problems such as image classification.
(See the Amazon SageMaker developer guide titled Image Classification Algorithm)
Option C is incorrect.
The Sequence-to-Sequence model is used to take a sequence of tokens and produces another sequence of tokens.
It is used for problems like language translation, text summarization, and speech-to-text.
(See the Amazon SageMaker developer guide titled Sequence-to-Sequence Algorithm)
Option D is incorrect.
The Neural Topic Model algorithm is used to organize documents into topics.
This type of model is not suited to image classification.
(See the Amazon SageMaker developer guide titled Neural Topic Model (NTM) Algorithm)
Reference:
Please see the Amazon SageMaker developer guide titled Use Amazon SageMaker Built-in Algorithms.
The best SageMaker model to use for this machine learning problem would be Image Classification.
Image Classification is a type of supervised learning that can be used to classify images based on their content. This model works by using a set of labeled images to train the model, which then learns to recognize patterns in new images and classify them accordingly.
In this case, the labeled images would be photos of dogs that have been tagged on Instagram and Twitter, and the model would be trained to recognize the different breeds of dogs based on the patterns it learns from these images. The model would then be able to classify new images of dogs based on their breed.
K-Means is an unsupervised learning algorithm that can be used for clustering data. This would not be a suitable model for this problem, as the goal is not to cluster the data into groups, but rather to classify the images based on their content.
Sequence-to-Sequence is a type of model that is used for tasks such as language translation, where the input is a sequence of words and the output is another sequence of words. This would not be a suitable model for this problem, as the input is an image and the output is a single label indicating the breed of the dog.
Neural Topic Model is a type of unsupervised learning algorithm that is used for topic modeling, where the goal is to discover the underlying topics in a set of documents. This would not be a suitable model for this problem, as the goal is not to discover topics in the images, but rather to classify them based on their content.
Therefore, Image Classification is the best SageMaker model to use for this machine learning problem.
