You work for a gaming company that develops and manages a popular massively multiplayer online (MMO) game. The game's environment is open-ended, and a large number of positions and moves can be taken

Question

Options

• AUse a Cloud TPU to optimize model training speed.
• BUse AI Platform Prediction with a NVIDIA GPU to make real-time predictions.
• CUse AI Platform Prediction with a high-CPU machine type to get a batch prediction for the
• DUse AI Platform Prediction with a high-memory machine type to get a batch prediction for the

• A
  3% (1)
• B
  81% (26)
• C
  9% (3)
• D
  6% (2)

Explanation

A is not correct because changing the training will not improve the prediction latency. B is correct because using a VM with a GPU and NVIDIA drivers enables you to use TensorRT. NVIDIA has developed TensorRT (an inference optimization library) for high-performance inference on GPUs. Google Cloud's Deep Learning VMs are ideal for this case because they have everything you need pre-installed. B is not correct because batch jobs do not satisfy the low-latency requirements for an online multiplayer game. D is not correct because batch jobs do not satisfy the low-latency requirements for an online multiplayer game. https://cloud.google.com/blog/products/ai-machine-learning/train-fast-on-tpu-serve-flexibly-on- gpu-switch-your-ml-infrastructure-to-suit-your-needs https://cloud.google.com/ai-platform/prediction/docs/machine-types-online-prediction https://cloud.google.com/compute/docs/gpus https://cloud.google.com/solutions/machine-learning/minimizing-predictive-serving-latency-in- machine-learning#precomputing_and_caching_predictions

No community discussion yet for this question.