AI0-001 AI Concepts and Techniques Practice Question
A company wants to classify images of products into categories. They have a large dataset of labeled images. Which TWO types of neural networks are most suitable for this task? (Select TWO.)
⚠ Common exam trap
The common mistake is assuming any general neural network can handle images, but RNNs and MLPs are not suited for spatial feature extraction despite being able to process image data.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Convolutional Neural Network (CNN)
Option B, Convolutional Neural Network (CNN), is correct because CNNs use convolutional and pooling layers to exploit spatial locality and translation invariance in images, making them the classic architecture for supervised image classification with large labeled datasets. Option D, Transformer (e.g., Vision Transformer), is also correct because a Vision Transformer splits an image into patches, embeds them, and applies self-attention to model global relationships, achieving state-of-the-art results on image classification when sufficient labeled data (or pretraining) is available. Option A, Generative Adversarial Network (GAN), is not appropriate here because GANs are generative models that learn to synthesize data via a generator-discriminator game rather than directly performing supervised category classification. Option C, Recurrent Neural Network (RNN), is unsuitable because RNNs are designed for sequential data such as text or time series and do not natively capture the 2D spatial structure of images. Option E, Multi-layer Perceptron (MLP), is not the best choice because fully connected layers ignore spatial hierarchy and typically underperform CNNs or Transformers on large-scale image classification.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Generative Adversarial Network (GAN)
Why it's wrong here
GANs generate new synthetic images from noise via adversarial training, so they cannot assign labels to existing product photos. They are tempting because they handle image data, but their purpose is image creation or augmentation, not classification; a supervised convolutional network would be the correct choice here.
- ✓
Convolutional Neural Network (CNN)
Why this is correct
Convolutional neural networks apply learned filters that exploit spatial locality and translation invariance in images, making them highly effective for classifying labelled product images. This satisfies the stem's requirement for a suitable architecture given a large labelled image dataset.
- ✗
Recurrent Neural Network (RNN)
Why it's wrong here
An RNN processes sequential or temporal data and has no mechanism for spatial feature extraction from images, so it cannot classify product photos effectively. It is tempting because RNNs are neural networks and handle labelled data, but they would be the correct choice for sequences such as text or time series, not image categories.
- ✓
Transformer (e.g., Vision Transformer)
Why this is correct
Vision Transformers split images into patches and apply self-attention across them, capturing global relationships that CNNs handle less directly. With a large labelled dataset, as the stem specifies, they achieve strong image classification accuracy and suit this task.
- ✗
Multi-layer Perceptron (MLP)
Why it's wrong here
A multi-layer perceptron treats image pixels as an unstructured flat vector, discarding spatial relationships and requiring far more parameters to learn features that convolutions capture directly. It is tempting as the general-purpose baseline for tabular classification, and would be correct for structured numeric or categorical data rather than large labelled image datasets.
About these practice questions
This AI0-001 question is part of Courseiva's 962-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI0-001 practice question is part of Courseiva's free CompTIA certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI0-001 exam.