Generative AI Leader Fundamentals of Generative AI Practice Question
During model evaluation, a team observes good performance on training data but poor on validation data. Which regularization technique is most appropriate to address this?
⚠ Common exam trap
Google Cloud often tests the distinction between techniques that improve generalization (regularization) versus those that improve optimization (learning rate, batch size), leading candidates to confuse data augmentation or hyperparameter tuning with regularization methods like dropout.
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
✓
Apply dropout
The scenario describes overfitting, where the model memorizes training data but fails to generalize to unseen validation data. Dropout is a regularization technique that randomly deactivates a fraction of neurons during training, forcing the network to learn more robust features and reducing co-adaptation, which directly mitigates overfitting.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Add more training data
Why it's wrong here
Adding training data enlarges the sample but applies no penalty or constraint to the model, so it does not directly regularise an already-overfitting network. It is tempting because more data usually improves generalisation, and would be correct when the dataset itself is too small or unrepresentative.
- ✗
Increase the learning rate
Why it's wrong here
Raising the learning rate increases the size of weight updates, which worsens the train-validation gap rather than constraining model capacity. It is tempting because a higher rate can escape poor local minima during optimisation, but that addresses underfitting, not the overfitting seen here.
- ✓
Apply dropout
Why this is correct
Dropout randomly deactivates units during training, forcing the network to learn redundant, distributed representations instead of memorising training samples. This regularisation narrows the gap between training and validation performance, directly addressing the poor generalisation the team observed during model evaluation.
- ✗
Use a larger batch size
Why it's wrong here
A larger batch size changes gradient variance and throughput, not model capacity, so it does not penalise the complex weights causing the train-validation gap. It is tempting because large batches stabilise training and speed up convergence, which suits throughput-constrained training runs rather than regularisation.
Go deeper
Related to this question
About these practice questions
This Generative AI Leader question is part of Courseiva's 1,008-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 Generative AI Leader practice question is part of Courseiva's free Google Cloud 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 Generative AI Leader exam.