Microsoft Azure AI Engineer Associate Certification Training

Syllabus of Microsoft Azure AI Engineer Associate Certification Online Trainiing Course

Module 1: Analyze solution requirement

• 1. Recommend Cognitive Services APIs to meet business requirements
• 2. Choosing a Microsoft cognitive services technology
• 3. Microsoft Azure Cognitive Services: The Big Picture
• 4. Microsoft Azure Cognitive Services: Custom Vision API
• 5. Precision versus Recall
• 6. automated-ml#precision-recall-chart
• 7. Performance measures in Azure ML: Accuracy, Precision, Recall and F1 Score

Module 2: Map security requirements to tools, technologies, and processes

• 1. Bot Service Compliance

Module 3: Select the software, services, and storage required to support a solution

• 1. Machine learning at scale learning-at-scale
• 2. Designing an Intelligent Edge in Microsoft Azure (By Jared Rhodes)
• 3. Azure IoT reference architecture
• 4. Azure IoT reference architecture (Detailed PDF)
• 5. Choosing a real-time message ingestion technology in Azure

Module 4: Connecting IoT Devices to Azure: IoT Hub and Event Hubs

• 1. Azure Databricks

Module 5: Sentiment analysis on streaming data using Azure Databricks

• 1. Build a real-time recommendation API on Azure
• 2. storage required to store logging, bot state data, and Cognitive Services output
• 3. Choose the right data store
• 4. Warehouse
• 5. Azure Data Lake Analytics
• 6. Azure Data Lake Store
• 7. Cosmos DB Global Distribution:
• 8. Install the Azure IoT Edge runtime on Debian-based Linux system
• 9. Deploy Azure IoT Edge modules from the Azure portal
• 10. Creating an image recognition solution with Azure IoT Edge and Azure Cognitive Services
• 11. IoT edge built-in modules
• 12. Stream Analytics
• 13. Another option for stream analytics is Apache Spark in Azure Databrick or HDInsigt, or Apache Storm in HDInsight
• 14. Apache Storm
• 15. Anomaly detection using machine learning in Azure Stream Analytics
• 16. Built-in ML based Anomaly Detection

Module 6: Anomaly detection in Azure Stream Analytics

• 1. Real-Time ML based Anomaly Detection in Azure Stream Analytics (same as above but demo with Raspberry Pi)
• 2. Anomaly Generator (Git)
• 3. Performing sentiment analysis by using Azure Stream Analytics and Azure Machine Learning Studio
• 4. Real-time analytics on IoT Edge with Azure Stream Analytics
• 5. Azure Stream Analytics now available on IoT Edge

Module 7: Design AI Solutions

Module 8: Design solutions that include one or more pipelines

• 1. What is Azure Machine Learning
• 2. Predict automobile price with the visual interface
• 3. Create and manage Azure Machine Learning service workspaces
• 4. AI Pipelines
• 5. Azure Machine Learning Pipeline
• 6. AML Samples:
• 7. Get Started with Azure Machine Learning
• 8. How to use Notebooks with Azure Machine Learning workspace
• 9. Choose a Compute target
• 10. Deploy a model to an Azure Kubernetes Service cluster
• 11. Deploy a model using a custom Docker image
• 12. Azure Data Factory
• 13. Data Science Virtual Machine
• 14. Data Science Virtual Machine
• 15. AI Data Science Virtual Machine
• 16. Learning Virtual Machine

Module 9: Design solutions that uses Cognitive Services

• 1. Cognitives Services Directory
• 2. Classify images with the Microsoft Custom Vision Service
• 3. Speech Service Documentation
• 4. Bing Web Search API Documentation
• 5. What is Custom Decision Service?

Module 10: Design solutions that implement the Bot Framework

• 1. Building a bot
• 2. Bot Framework Emulator
• 3. Data sources for QnA Maker content
• 4. Best practices of a QnA Maker knowledge base
• 5. LUIS (Language Understanding Intelligent Services)
• 6. Entity types and their purposes in LUIS
• 7. Composite entity
• 8. List entity
• 9. Enterprise-grade conversational bot

Module 11: Design the compute infrastructure to support a solution

• 1. What are field-programmable gate arrays (FPGA)
• 2. Inside the Microsoft FPGA-based configurable cloud
• 3. Hyperscale hardware: ML at scale on top of Azure + FPGA
• 4. GPUs vs CPUs for deployment of deep learning models by Fidan Boylu Uz
• 4. Reference architecture: Machine Learning model training with AKS
• 5. Deploy Deep Learning CNN on Kubernetes Cluster with GPUs – AML version
• 6. Deploying Deep Learning Models on Kubernetes with GPUs
• 7. Design Data for Governance, compliance, integrity & security

• 1. IoT Hub
• 2. AML Services
• 3. AML Sample

Module 14: VS Code extension for Azure Machine Learning

Module 15: Integrate AI services with solution components

• 1. Azure IoT reference architecture
• 2.Add authentication to your bot via Azure Bot Service

Module 16: Monitor and Evaluate the AI environment

• 1. Overview of alerts in Microsoft Azure
• 2. Monitor your Azure Machine Learning models with Application Insights
• 3. Add telemetry to your bot
• 4. Bot analytics

Module 17: Understand automated machine learning results

• 1. Other useful materials
• 2. Developing AI Models in Microsoft Azure
• 3. Managing Microsoft Azure AI Solutions
• 4. Microsoft Azure Developer: Creating and Integrating AI with Azure Services
• 5. AI-100: Designing and Implementing an Azure AI Solution — Study Guide
• 6. MLOps Workshop
• 7. Microsoft Cloud Workshop library
• 8. Creating an image recognition solution with Azure IoT Edge and Azure Cognitive Services