PMLE - Scaling Prototypes Into ML Models - Section 3.1

Choose the model type and Google Cloud product given cost, complexity, latency, and scalability, selecting among options such as ARIMA, DNN, and LLM and products such as Agent Platform AutoML, BigQuery ML, and Agent Platform Pipelines, and deciding deployment and interpretability strategies.

Compare ARIMA, DNN, and LLM architectures against cost, latency, scalability, and complexity constraints, and match each to the right Google Cloud product such as Agent Platform AutoML or BigQuery ML. Choose a deployment and interpretability strategy that satisfies both performance requirements and explainability needs.

ARIMA, DNN, and LLMAgent Platform AutoMLDeployment strategyInterpretability

More in this domain

Train models by organising structured and unstructured data on Cloud Storage and BigQuery, ingesting from various sources, using SDKs such as Agent Platform custom training, Kubeflow on GKE, AutoML, and Tabular Workflows, troubleshooting training failures, tuning hyperparameters, and fine-tuning foundation models.Section 3.2
Choose appropriate hardware for training, evaluating CPU, GPU, and TPU options and understanding distributed training across GPUs and TPUs using data and model parallelism strategies.Section 3.3

Back to all Scaling Prototypes Into ML Models objectives, or the PMLE cert hub.

Examworthy is not affiliated with or endorsed by Google Cloud. Original, blueprint-aligned practice material only.