Tässä koulutuksessa käydään läpi tavat tehdä koneoppimista Azuressa sekä kuinka tehdään generative AI appeja Azure AI Foundryllä. Koulutuksessa käydään läpi koko ML Pipeline: Datan käsittely, laskentaympäristön pystyttäminen, algoritimien automatisoitu valinta, hyperparametrien virittäminen, tuotantoon siirto, monitorointi jne.
Lisäksi koulutuksessa perehdytään generative AI appien tekoon Azure Ai Foundryllä ja toteutetaan kielimalleja käyttäviä keskustelusovelluksia sekä kuinka oma data tuodaan mukaan prosessiin.
Tavoite
Opi kuinka teet modernia koneoppimista sekä generative AI appeja Azuressa.
Kenelle
Tämä koulutus on suunnattu data- ja IT -asiantuntijarooleille mm. Data Scientist, Data Engineer, Data Analyst, IT-Architect.
Koulutus edellyttää Python-kielen perusteiden sekä Machine Learning -perusteiden tuntemusta esimerkiksi Azure AI Fundamentals -kokonaisuutta tai vastaavia taitoja.
Lisätiedot
Koulutus valmentaa Microsoftin viralliseen Exam DP-100 Designing and Implementing a Data Science Solution on Azure -sertifiointitestiin.
Koulutuksen sisältö
Explore the Azure Machine Learning Workspace
- Explore Azure Machine Learning workspace resources and assets
- Explore developer tools for workspace interaction
Make data available in Azure Machine Learning
- Create Datastores
- Create Data Assets
Work with compute in Azure Machine Learning
- Work with compute targets in Azure Machine Learning
- Work with environments in Azure Machine Learning
Use no-code machine learning with the Azure Machine Learning Designer
- Explore Automate Machine Learning
- Find the best classification model with Automated Machine Learning
Use notebooks for experimentation in Azure Machine Learning
- Track model training in notebooks with MLflow
Train models with scripts in Azure Machine Learning
- 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
Optimize model training in Azure Machine Learning
- Run pipelines in Azure Machine Learning
Manage and review models in Azure Machine Learning
- Register an MLflow model in Azure Machine Learning
- Manage and compare models in Azure Machine Learning
Deploy and consume models with Azure Machine Learning
- Register an MLflow model in Azure Machine Learning
- Manage and compare models in Azure Machine Learning
Plan and prepare to develop AI solutions on Azure
- Describe Azure AI Services and considerations for using them
- Describe Azure AI Foundry and considerations for using it
Choose and deploy models from the model catalog in Azure AI Foundry portal
- Select a language model from the model catalog
- Deploy a model to an endpoint
- Test a model and improve the performance of the model
Get started with prompt flow to develop language model apps in the Azure AI Foundry
- Understand the development lifecycle when creating language model applications
- Understand what a flow is in prompt flow
- Explore the core components when working with prompt flow
Build a RAG-based agent with your own data using Azure AI Foundry
- Identify the need to ground your language model with Retrieval Augmented Generation (RAG)
- Index your data with Azure AI Search to make it searchable for language models
- Build an agent using RAG on your own data in the Azure AI Foundry portal
Fine-tune a language model with Azure AI Foundry
- Prepare your data to fine-tune a chat completion model
- Fine-tune a base model in the Azure AI Foundry portal
Evaluate the performance of generative AI apps with Azure AI Foundry
- Understand model benchmarks
- Perform manual evaluations
- Assess your generative AI apps with AI-assisted metrics
- Configure evaluation flows in the Azure AI Foundry portal
Responsible generative AI
- Identify and prioritize potential harms relevant to a generative AI solution
- Measure the presence of harms in a generative AI solution
- Mitigate harms in a generative AI solution
- Prepare to deploy and operate a generative AI solution responsibly
Avainsanat
Azure Machine Learning, Data Science, Generative AI