AWS Certified Machine Learning – Specialty — Question 357

A company’s machine learning (ML) team needs to build a system that can detect whether people in a collection of images are wearing the company’s logo. The company has a set of labeled training data.

Which algorithm should the ML team use to meet this requirement?

Answer options

• A. Principal component analysis (PCA)
• B. Recurrent neural network (RNN)
• C. К-nearest neighbors (k-NN)
• D. Convolutional neural network (CNN)

Correct answer: D

Explanation

Convolutional neural networks (CNNs) are the industry standard for computer vision tasks such as image classification and object detection because they can effectively extract spatial features. Principal component analysis (PCA) is used for dimensionality reduction, and К-nearest neighbors (k-NN) is not suitable for complex image classification tasks. Recurrent neural networks (RNNs) are designed for sequential or temporal data rather than static image processing.