官方技术资料：Microsoft（第 10 页）
官方技术资料 · Microsoft：共 312 条，本页为第 136–150 条。
Lag features for time-series forecasting in AutoML
Explore how automated machine learning (AutoML) in Azure Machine Learning creates lag and rolling window aggregation to forecast time-series regression models.
证据用途：用于理解、实现、选型、可靠性、安全或迁移判断。
使用边界：只直接证明 Microsoft 的实现与声明；预览功能和产品生命周期使用前应复核
关联概念：supervised-learning · rnn
链接复核时间：2026-09-24
Overview of forecasting methods in AutoML
Learn how AutoML in Azure Machine Learning uses machine learning to build forecasting models, including time series or regression models for predictions.
证据用途：用于理解、实现、选型、可靠性、安全或迁移判断。
使用边界：只直接证明 Microsoft 的实现与声明；预览功能和产品生命周期使用前应复核
关联概念：supervised-learning · rnn
链接复核时间：2026-09-24
Model sweeping and selection for forecasting in AutoML
Explore how you can use automated machine learning (AutoML) in Azure Machine Learning to search for (sweep) and select forecasting models.
证据用途：用于理解、实现、选型、可靠性、安全或迁移判断。
使用边界：只直接证明 Microsoft 的实现与声明；预览功能和产品生命周期使用前应复核
关联概念：supervised-learning · rnn
链接复核时间：2026-09-24
Make data-driven policies and influence decision-making
Make data-driven decisions and policies with the Responsible AI dashboard's integration of the causal analysis tool EconML.
证据用途：用于理解、实现、选型、可靠性、安全或迁移判断。
使用边界：只直接证明 Microsoft 的实现与声明；预览功能和产品生命周期使用前应复核
关联概念：interpretability · supervised-learning
链接复核时间：2026-09-24
Counterfactuals analysis and what-if
Generate diverse counterfactual examples with feature perturbations to see minimal changes required to achieve desired prediction with the Responsible AI dashboard's integration of DiCE machine learning.
证据用途：用于理解、实现、选型、可靠性、安全或迁移判断。
使用边界：只直接证明 Microsoft 的实现与声明；预览功能和产品生命周期使用前应复核
关联概念：interpretability · supervised-learning
链接复核时间：2026-09-24
Model performance and fairness
Learn about machine learning fairness and how the Fairlearn Python package can help you assess and mitigate unfairness.
证据用途：用于理解、实现、选型、可靠性、安全或迁移判断。
使用边界：只直接证明 Microsoft 的实现与声明；预览功能和产品生命周期使用前应复核
关联概念：governance · bias-fairness · interpretability
链接复核时间：2026-09-24
Machine learning registries for MLOps
Learn about Azure Machine Learning registries and their role in scaling MLOps across different environments.
证据用途：用于理解、实现、选型、可靠性、安全或迁移判断。
使用边界：只直接证明 Microsoft 的实现与声明；预览功能和产品生命周期使用前应复核
关联概念：agent · agent-frameworks
链接复核时间：2026-09-24
Azure Machine Learning model monitoring
Learn about monitoring the performance of models deployed to production on Azure Machine Learning, including lookback windows, monitoring signals, and metrics.
证据用途：用于理解、实现、选型、可靠性、安全或迁移判断。
使用边界：只直接证明 Microsoft 的实现与声明；预览功能和产品生命周期使用前应复核
关联概念：observability · deployment
链接复核时间：2026-09-24
What is Responsible AI?
Learn what Responsible AI is and how to use it with Azure Machine Learning to understand models, protect data, and control the model lifecycle.
证据用途：用于理解、实现、选型、可靠性、安全或迁移判断。
使用边界：只直接证明 Microsoft 的实现与声明；预览功能和产品生命周期使用前应复核
关联概念：governance · bias-fairness · interpretability
链接复核时间：2026-09-24
Assess AI systems by using the Responsible AI dashboard
Learn how to use the comprehensive UI and SDK/YAML components in the Responsible AI dashboard to debug your machine learning models and make data-driven decisions.
证据用途：用于理解、实现、选型、可靠性、安全或迁移判断。
使用边界：只直接证明 Microsoft 的实现与声明；预览功能和产品生命周期使用前应复核
关联概念：governance · bias-fairness · interpretability
链接复核时间：2026-09-24
Share Responsible AI insights using the Responsible AI scorecard (preview)
Learn about how to use the Responsible AI scorecard to share responsible AI insights from your machine learning models and make data-driven decisions with nontechnical and technical stakeholders.
证据用途：用于理解、实现、选型、可靠性、安全或迁移判断。
使用边界：只直接证明 Microsoft 的实现与声明；预览功能和产品生命周期使用前应复核
关联概念：governance · bias-fairness · interpretability
链接复核时间：2026-09-24
Make predictions with ONNX on computer vision models from AutoML
Use ONNX with Azure Machine Learning automated ML to make predictions on computer vision models for classification, object detection, and instance segmentation.
证据用途：用于理解、实现、选型、可靠性、安全或迁移判断。
使用边界：只直接证明 Microsoft 的实现与声明；预览功能和产品生命周期使用前应复核
关联概念：supervised-learning · rnn
链接复核时间：2026-09-24
Model interpretability
Learn how your machine learning model makes predictions during training and inferencing by using the Azure Machine Learning CLI and Python SDK.
证据用途：用于理解、实现、选型、可靠性、安全或迁移判断。
使用边界：只直接证明 Microsoft 的实现与声明；预览功能和产品生命周期使用前应复核
关联概念：interpretability · supervised-learning
链接复核时间：2026-09-24
Prepare data for computer vision tasks by using automated machine learning
Learn about image data preparation for Azure Machine Learning to train computer vision models on classification, object detection, and segmentation.
证据用途：用于理解、实现、选型、可靠性、安全或迁移判断。
使用边界：只直接证明 Microsoft 的实现与声明；预览功能和产品生命周期使用前应复核
关联概念：supervised-learning · rnn
链接复核时间：2026-09-24
Hyperparameter tuning a model (v2)
Discover how to define search spaces, choose sampling algorithms, and configure early termination policies for hyperparameter tuning in Azure ML.
证据用途：用于理解、实现、选型、可靠性、安全或迁移判断。
使用边界：只直接证明 Microsoft 的实现与声明；预览功能和产品生命周期使用前应复核
关联概念：supervised-learning · regularization
链接复核时间：2026-09-24