AI0-001 Machine Learning and Deep Learning Practice Question
A company is building a computer vision system to detect defects in manufactured parts. They have 10,000 labeled images per class (defective and non-defective). They want to achieve high accuracy with limited computational resources. Which deep learning architecture and approach is most appropriate?
⚠ Common exam trap
CompTIA AI often tests the misconception that more layers or training from scratch always yields better accuracy, when in reality transfer learning with a pre-trained model is the most practical choice for moderate datasets and limited compute.
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
✓
Use a pre-trained VGG16 and fine-tune the last few layers
Using a pre-trained VGG16 and fine-tuning the last few layers leverages transfer learning, which is ideal when you have a moderate-sized labeled dataset (10,000 images per class) and limited computational resources. The pre-trained model already captures general visual features from ImageNet, so only the task-specific layers need to be trained, reducing training time and resource requirements while still achieving high accuracy.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Train a custom CNN from scratch with many layers
Why it's wrong here
A deep custom CNN trained from scratch demands large compute and data to converge, conflicting with the limited-resource requirement. Building from scratch suits novel domains with abundant data, but transfer learning from a pre-trained CNN gives high accuracy here with far less training cost.
- ✗
Use a decision tree ensemble
Why it's wrong here
A decision tree ensemble operates on engineered tabular features and cannot learn spatial hierarchies from raw pixels, so defect detection accuracy would suffer. Ensembles suit structured tabular classification, whereas convolutional layers are needed to capture the local patterns that distinguish defective from non-defective parts.
- ✓
Use a pre-trained VGG16 and fine-tune the last few layers
Why this is correct
Transfer learning with a pre-trained VGG16 exploits features already learned from large image datasets, so fine-tuning only the final layers reaches high defect-detection accuracy with far less training data and compute than training a deep network from scratch.
- ✗
Use an RNN to process image sequences
Why it's wrong here
An RNN processes sequential or temporal data, so it cannot exploit the two-dimensional spatial structure of defect images. RNNs are the right choice for sequences such as video frames or time series, but a CNN is required here to extract spatial features from 10,000 labelled images per class.
About these practice questions
One of 962 original AI0-001 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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.