NCP-ADS 무료 덤프문제 온라인 액세스

Which of the following data normalization techniques is most appropriate when the dataset contains outliers, and you want to minimize the influence of those outliers on the model performance?

• A.Log Transformation
• B.Min-Max Scaling
• C.Robust Scaling
• D.Z-score Standardization

You need to deploy a machine learning model on a GPU-equipped system. The GPU has 16GB of VRAM, and the model requires approximately 12GB of memory during inference. However, additional system processes and other applications consume 5GB of VRAM.
What would happen if you attempt to run inference without making any optimizations, and how should you resolve the issue?

• A.Switching from a GPU to CPU inference will resolve memory issues without performance loss
• B.The model will run without issues because 16GB of VRAM is sufficient for a 12GB model
• C.The model will fail to run due to out-of-memory (OOM) errors, and using a smaller batch size can help reduce memory usage
• D.The model will run successfully but with reduced performance due to memory fragmentation

A machine learning engineer is tasked with deploying a real-time image classification model as part of an MLOps pipeline. The model requires low-latency inference and must handle high-throughput requests efficiently.
Which of the following deployment strategies is the most suitable for leveraging GPU acceleration?

• A.Using an Apache Spark cluster with distributed CPU-based inference.
• B.Deploying the model using NVIDIA Triton Inference Server with TensorRT optimizations.
• C.Using a REST API wrapper to load the model dynamically into memory for each request.
• D.Running the model inference on a multi-core CPU server with batch processing enabled.

You need to set up an isolated, GPU-accelerated environment for a deep learning project that requires specific CUDA, cuDNN, and RAPIDS versions.
Which of the following best ensures a reproducible environment using Docker?

• A.Use the nvidia/cuda base image and specify the required RAPIDS and deep learning libraries in a Dockerfile.
• B.Use a system-wide CUDA installation and mount the /usr/local/cuda directory into the container to provide GPU support.
• C.Build a container from an Ubuntu base image and manually install all dependencies without specifying versions.
• D.Install NVIDIA drivers manually inside a Docker container every time it runs.

You are training a deep learning model for image classification and want to optimize its hyperparameters, including learning rate, batch size, and number of layers.
Which of the following techniques is the most effective for efficiently searching through a high- dimensional hyperparameter space?

• A.Bayesian Optimization
• B.Random Search
• C.Gradient Descent
• D.Grid Search