Applied AI on Microsoft Azure
Training Course
This course covers the basics of machine learning, cognitive services, and how to build AI solutions on Azure. It includes hands-on exercises and projects to apply AI concepts in real-world scenarios.
Instructor:
Target audience
Business professionals, developers, and anyone keen to explore and leverage the capabilities of AI in various business applications.
Skills you'll gain
- Proficiency in leveraging the Microsoft AI platform, including Azure AI Services and Azure Machine Learning, for developing AI solutions.
- Competence in utilizing Azure AI Studio as a centralized hub for building, deploying, and managing AI models.
- Understanding of Microsoft Fabric and its role in enabling seamless integration and communication between AI components.
- Ability to implement AI solutions using AI Builder in Power Automate, expanding automation capabilities with AI-driven workflows.
- Proficiency in using ML.NET and Semantic Kernel for custom machine learning model development and advanced natural language processing tasks.
Course modules
Module 1. Introduction to Microsoft AI platform
Dive into the fascinating world of artificial intelligence and machine learning, understanding their foundational concepts and significance. This module sheds light on the myriad applications and benefits of AI, especially in business settings. Moreover, participants will get an overview of Microsoft's AI platform, which plays a pivotal role in enabling applied AI solutions in the modern digital landscape.
Module 2. Azure AI Services
Azure AI Services is a suite of cloud-based artificial intelligence services that enable developers to infuse cognitive intelligence
into applications without needing extensive AI or data science expertise.
It offers a range of prebuilt and customizable APIs and models for tasks such as natural language processing, search, monitoring, translation, speech, vision, and decision-making.
Module 3. Azure Machine Learning
Azure Machine Learning is a service that accelerates the machine learning project lifecycle. It caters to ML professionals, data scientists, and engineers, facilitating their workflows with tools for training,
deploying models, and managing machine learning operations (MLOps). The platform supports model creation from various open-source platforms like PyTorch,
TensorFlow, or scikit-learn, and offers MLOps tools for model monitoring, retraining, and redeployment.
Module 4. Azure AI Studio
Azure AI Studio is a cutting-edge platform designed to empower developers and AI enthusiasts to build, evaluate, and deploy generative AI solutions and custom copilots.
It serves as an all-in-one AI hub, offering a suite of tools and machine learning models that are grounded in responsible AI practices. With Azure AI Studio, users can seamlessly transition
from exploring AI capabilities to building and customizing their own AI applications. The platform supports a collaborative environment, providing enterprise-grade security and the ability to organize projects efficiently.
Module 5. Microsoft Fabric
Microsoft Fabric is an integrated analytics platform that simplifies enterprise data management and analysis. It combines services like Azure Data Factory, Azure Synapse Analytics, and Power BI into a unified solution, streamlining the process from data ingestion to business intelligence. With a focus on real-time analytics and data science, Microsoft Fabric offers a comprehensive suite of tools for data lake, data engineering, and data integration.
Module 6. AI Builder in Power Automate
AI Builder in Power Automate is a feature of the Microsoft Power Platform that enables users to enhance their automated workflows with artificial intelligence.
With AI Builder, you can either utilize prebuilt AI models for common business scenarios or create custom models tailored to your specific needs.
Module 7. ML.NET
ML.NET is a robust, open-source machine learning framework specifically designed for .NET developers.
It enables the creation of custom machine learning models using C# or F# without requiring expertise in data science.
The framework supports a variety of machine learning tasks, such as sentiment analysis, price prediction, fraud detection, and more.
Module 8. Semantic Kernel
Semantic Kernel is an open-source SDK that enables the creation of AI agents capable of interfacing with existing code.
It’s highly adaptable, supporting integration with models from OpenAI, Azure OpenAI, Hugging Face, and more.
Semantic Kernel acts as an orchestration layer, allowing for the seamless combination of AI models and plugins, thus facilitating the development of new user experiences.
What our customers say: