NCA-GENL Core Machine Learning and AI Knowledge Practice Question
A machine learning engineer is preprocessing a dataset for a generative AI model and wants to ensure that the input features have a similar scale. Which technique is most appropriate?
⚠ Common exam trap
Test-takers frequently confuse data cleaning (outlier removal) with feature scaling, which are distinct preprocessing steps.
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
✓
Normalize numerical features to have zero mean and unit variance.
Normalizing numerical features to zero mean and unit variance brings them to a similar scale, which aids optimization and model performance. One-hot encoding is for categorical data, outlier removal is for data cleaning, and learning rate is unrelated to feature scaling. Thus, normalization is the correct preprocessing technique.
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 learning rate during training.
Why it's wrong here
The learning rate is a hyperparameter for optimization and does not affect feature scaling. A higher learning rate might cause instability if features are not scaled, but it does not solve the scaling issue. Preprocessing steps like normalization should be applied before training, independent of the learning rate.
- ✓
Normalize numerical features to have zero mean and unit variance.
Why this is correct
Normalization (standardization) transforms numerical features to have zero mean and unit variance, ensuring they are on a similar scale. This helps gradient-based optimization converge faster and prevents features with larger magnitudes from dominating. It is a standard preprocessing step for many machine learning and generative models.
- ✗
Remove outliers from the dataset.
Why it's wrong here
Removing outliers can help with robustness but does not directly address feature scaling. Outliers may affect the mean and variance, but the primary goal is to scale features, not to remove data points. While outlier removal can be part of preprocessing, it is not the technique for achieving similar scales across features.
- ✗
Apply one-hot encoding to all categorical features.
Why it's wrong here
One-hot encoding is used for categorical variables to convert them into binary vectors, but it does not scale numerical features. It can actually increase dimensionality and may lead to sparse representations. The goal is to bring features to a similar scale, which one-hot encoding does not achieve for continuous variables.
About these practice questions
Courseiva writes every NCA-GENL question from scratch — 367 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. 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 NVIDIA exam blueprint
This NCA-GENL practice question is part of Courseiva's free NVIDIA 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 NCA-GENL exam.