A data science team is deploying a deep learning model for real-time inference. The model is optimized for inference on an NVIDIA A100 GPU, but the team notices that inference latency is higher than expected.
Which of the following optimizations is most effective in reducing inference latency?

• A. Reduce the model size by randomly pruning neurons without retraining.
• B. Increase the batch size significantly to improve GPU utilization.
• C. Use mixed-precision inference with TensorRT to accelerate computation.
• D. Enable CPU offloading to balance the workload between the CPU and GPU.

You are working with a dataset where numerical features have different scales. To ensure uniformity across features, you decide to standardize the data using NVIDIA RAPIDS cuML.
Which of the following methods correctly standardizes the data in a GPU-accelerated manner?

• A. df = df.apply(lambda x: (x - x.mean()) / x.std(), axis=1)
• B. df = (df - df.mean()) / df.std()
• C. df = (df - df.min()) / (df.max() - df.min())
• D. 1. scaler = cuml.preprocessing.StandardScaler() 2. df = scaler.fit_transform(df)

You are working on an AI-driven customer behavior prediction project.
According to the CRISP-DM (Cross Industry Standard Process for Data Mining) methodology, what is the most critical task to complete during the Data Understanding phase?

• A. Identifying and preparing feature engineering strategies to improve model accuracy.
• B. Selecting the most appropriate machine learning algorithm for the prediction task.
• C. Acquiring and exploring the dataset to assess quality, completeness, and potential biases.
• D. Deploying the model into a production environment for real-time inference.

A machine learning engineer runs NVIDIA DLProf to analyze the performance of a deep learning model and receives a report indicating high GPU idle time.
What is the most likely cause of this issue?

• A. The model is experiencing data loading bottlenecks, causing the GPU to wait for input batches.
• B. The GPU is not powerful enough to process the deep learning model efficiently.
• C. The CUDA cores are overheating, leading to automatic throttling of computations.
• D. The batch size is too large, leading to excessive GPU memory utilization and slow processing.