AI0-001 AI Concepts and Techniques Practice Question
A team is training a recurrent neural network (RNN) with LSTM units to predict stock prices. The validation loss is significantly higher than the training loss. Which action is MOST likely to reduce the gap?
⚠ Common exam trap
AI0-001 often tests the diagnosis of overfitting versus underfitting; candidates may pick increasing epochs or units thinking more training will help, but those actions worsen overfitting when the validation loss is already higher than training loss.
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
✓
Increase the dropout rate in LSTM layers
A significant gap between training and validation loss indicates overfitting, where the model memorizes training data but fails to generalize. Increasing dropout in LSTM layers is a regularization technique that randomly deactivates neurons during training, forcing the network to learn more robust features and reducing overfitting. This directly addresses the gap by improving validation performance.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increase the number of LSTM units
Why it's wrong here
Adding LSTM units raises model capacity, which typically widens the train-validation gap by enabling further memorisation of training sequences rather than closing it. Capacity increases suit underfitting, where both losses are high; here regularisation, dropout or early stopping addresses the overfitting the stem describes.
- ✗
Increase the number of training epochs
Why it's wrong here
More epochs let the network continue fitting training data, so training loss falls while validation loss plateaus or rises, enlarging the gap. Extra epochs suit underfitting, where both losses remain high and the model has not yet converged; this stem shows the opposite pattern.
- ✗
Reduce the sequence length
Why it's wrong here
Shortening sequences discards temporal dependencies the LSTM needs, degrading training and validation alike without addressing the memorisation causing the gap. Sequence reduction suits memory or compute constraints, or vanishing-gradient problems on very long inputs, not an overfitting diagnosis.
- ✓
Increase the dropout rate in LSTM layers
Why this is correct
Dropout randomly deactivates LSTM units during training, preventing the network from relying on particular hidden-state pathways and reducing variance. The validation loss exceeding training loss indicates overfitting, so increasing dropout regularises the recurrent layers and narrows that generalisation gap.
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 and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official CompTIA exam blueprint
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.