Designing and Implementing a Data Science Solution on Azure (DP-100)

Leer hoe je Microsoft Azure inzet om jouw data science projecten een boost te geven

Beschrijving

Je leert machine learning oplossingen op cloud-schaal te ontwikkelen en onderhouden door Azure Machine Learning in te zetten. Je gebruikt Azure Machine Learning en MLflow om data ingestion, data preparation, model training, model deployment en monitoring toe te passen, met gebruik van je bestaande Python en machine learning kennis.

Deze training geldt ook als voorbereiding voor het gelijknamige examen (DP-100) en de bijbehorende certificering Azure Data Scientist Associate.

Onderwerpen

Understand the machine learning process and how it can be implemented.

Lessons

• Understand the machine learning process
• Choose the service and compute required
• Case studies

You explore and configure the Azure Machine Learning workspace. Learn how you can create a workspace and what you can do with it. Explore the various developer tools you can use to interact with the workspace. Configure the workspace for machine learning workloads by creating data assets and compute resources.

Lessons

• Explore Azure Machine Learning workspace resources and assets
• Explore developer tools for workspace interaction
• Make data available in Azure Machine Learning
• Work with compute targets in Azure Machine Learning
• Work with environments in Azure Machine Learning

Learn how to find the best model with automated machine learning (AutoML) and by experimenting in notebooks.

Lessons

• Find the best classification model with Automated Machine Learning
• Track model training in Jupyter notebooks with MLflow

Learn how to optimize model training in Azure Machine Learning by using scripts, jobs, components and pipelines.

Lessons

• Run a training script as a command job in Azure Machine Learning
• Track model training with MLflow in jobs
• Perform hyperparameter tuning with Azure Machine Learning
• Run pipelines in Azure Machine Learning

Learn how to manage and review models in Azure Machine Learning by using MLflow to store your model files and using responsible AI features to evaluate your models.

Lessons

• Register an MLflow model in Azure Machine Learning
• Create and explore the Responsible AI dashboard for a model in Azure Machine Learning

Learn how to deploy a model to an endpoint. When you deploy a model, you can get real-time or batch predictions by calling the endpoint.

Lessons

• Deploy a model to a managed online endpoint
• Deploy a model to a batch endpoint

Learn how to optimize language models from the AI Foundry through different techniques.

Lessons

• Explore and deploy models from the model catalog
• Optimize model performance through prompt engineering
• Optimize through Retrieval Augmented Generation (RAG)
• Optimize through fine-tuning