MLA-C01 Deployment and Orchestration of ML Workflows Practice Question
A team is optimizing a deep learning model for deployment on SageMaker using SageMaker Neo. Which THREE of the following are valid optimization techniques that Neo can apply? (Choose THREE.)
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
✓
Pruning (removing redundant weights)
SageMaker Neo performs hardware-specific optimizations including quantisation (reducing precision), pruning (removing redundant weights), and operator fusion (combining operations). Knowledge distillation is a training-time technique, not part of Neo. Hyperparameter tuning is done by SageMaker Tuning jobs, not Neo.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Pruning (removing redundant weights)
Why this is correct
Neo can prune model weights to reduce model size and computational cost.
- ✓
Operator fusion (combining adjacent operations)
Why this is correct
Neo fuses operations to reduce kernel launch overhead and improve memory access.
- ✗
Knowledge distillation
Why it's wrong here
Knowledge distillation is a training method, not a compilation optimization applied by Neo.
- ✗
Hyperparameter tuning
Why it's wrong here
Hyperparameter tuning is performed by SageMaker Automatic Model Tuning, not Neo.
- ✓
Quantisation (e.g., FP16, INT8)
Why this is correct
Neo can quantize models to reduce memory and improve speed.
Go deeper
Related to this question
About these practice questions
This MLA-C01 question is part of Courseiva's 835-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 →
Same concept, more angles
1 more way this is tested on MLA-C01
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. A machine learning team needs to deploy a PyTorch model that has been compiled with SageMaker Neo to improve inference performance on edge devices. Which TWO statements about SageMaker Neo are correct? (Select TWO.)
medium- ✓ A.Neo reduces model inference latency through optimization techniques
- B.Neo requires the model to be trained on SageMaker
- ✓ C.Neo compiles models for a specific hardware target, such as Intel or ARM
- D.Neo can only compile models trained with SageMaker built-in algorithms
- E.Neo automatically scales SageMaker endpoints based on demand
Why A: SageMaker Neo optimizes models for specific hardware targets (e.g., ARM, Intel, NVIDIA) and reduces latency. It does not require training frameworks; it compiles trained models. It does not automatically scale endpoints. It is not limited to built-in algorithms.
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This MLA-C01 practice question is part of Courseiva's free Amazon Web Services 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 MLA-C01 exam.