AI AI Engineer: MLOps and Model Deployment 3

Question 1

What is the purpose of 'model quantization' in the context of ML deployment?

Accepted Answer

To reduce model size and inference time by using lower-precision arithmetic

Answer

To increase model accuracy

Answer

To add more layers to the neural network

Answer

To balance load across multiple servers

Question 2

Which Python library is widely used for building ML pipelines that can be tracked and reproduced?

Accepted Answer

DVC (Data Version Control)

Answer

Flask

Answer

FastAPI

Answer

Celery

Question 3

What does 'SLA' stand for in the context of ML model serving?

Accepted Answer

Service Level Agreement

Answer

Sparse Layer Algorithm

Answer

Statistical Learning Accuracy

Answer

Supervised Label Annotation

Question 4

In MLOps, what does 'continuous training' (CT) refer to?

Accepted Answer

Automatically retraining models on new data triggered by schedule or drift detection

Answer

Training a model without stopping until convergence

Answer

Using GPUs continuously for faster training

Answer

Streaming training data in real time

Question 5

Which serving framework is designed for high-performance, production-grade deployment of ML models, supporting REST and gRPC?

Accepted Answer

TensorFlow Serving

Answer

Jupyter Notebook

Answer

Pandas

Answer

Scikit-learn

Question 6

What is the main benefit of using a directed acyclic graph (DAG) to represent an ML pipeline?

Accepted Answer

It explicitly defines task dependencies, enabling parallel execution and reproducibility

Answer

It increases model accuracy

Answer

It reduces training data size

Answer

It compresses model weights