NCP-ADS 試験問題を無料オンラインアクセス

A financial services company is deploying an AI-driven risk assessment model using NVIDIA GPUs on a cloud platform. To optimize resource utilization and cost efficiency, they need to determine the best GPU deployment strategy.
Which of the following is the most effective approach?

• A.Run all AI workloads on a single large GPU instance without any partitioning or workload separation.
• B.Deploy the model using NVIDIAAI Enterprise with MIG (Multi-Instance GPU) to allocate multiple workloads on a single GPU efficiently.
• C.Choose an on-demand cloud instance with an outdated GPU model to reduce costs, even if performance is compromised.
• D.Deploy separate full-GPU instances for each workload, even if they have variable compute demands.

A data scientist is working with a large dataset for a machine learning model and wants to accelerate feature engineering using a GPU.
Which of the following approaches will provide the most significant performance boost when using GPU acceleration?

• A.Using RAPIDS cuDF and cuML libraries to perform feature transformations on a GPU.
• B.Using a single-threaded feature extraction approach to avoid overhead from parallelization.
• C.Using traditional pandas DataFrames and NumPy operations optimized for CPU processing.
• D.Reducing dataset size by randomly removing data points without considering class balance.

You are working on a machine learning dataset with millions of rows and want to optimize performance on a GPU using CuDF. One of the features in your dataset represents categorical data with a limited number of unique values.
Which of the following data types should you use to maximize performance while reducing memory usage?

• A.category
• B.object (string)
• C.int64
• D.bool

You are working with a large dataset in a GPU-accelerated environment, and one of the columns, revenue, contains numeric values representing the annual revenue for companies. The revenue values are in the billions of dollars.
Which of the following is the most memory-efficient data type for the revenue column in a cuDF DataFrame?

• A.df['revenue'] = df['revenue'].astype('uint32')
• B.df['revenue'] = df['revenue'].astype('float64')
• C.df['revenue'] = df['revenue'].astype('float32')
• D.df['revenue'] = df['revenue'].astype('int64')

A data science team is using NVIDIA GPUs to accelerate their AI workflow for a fraud detection system. They follow the CRISP-DM methodology to ensure a structured approach to the project.
During the Data Preparation phase, what is the most effective way to leverage NVIDIA technologies?

• A.Perform all data transformation on a single CPU core to ensure stability before deploying to GPU- accelerated training.
• B.Ignore feature engineering and feed raw data directly into the model, relying on deep learning to extract relevant features.
• C.Use NVIDIA RAPIDS to preprocess large-scale transaction datasets efficiently on GPUs before training the model.
• D.Manually clean and transform data using traditional CPU-based processing tools like pandas, then transfer the data to the GPU only for training.