Explore the diverse and powerful world of core generative AI. This course provides a comprehensive survey of the fundamental models that power modern AI, including Generative Adversarial Networks (GANs), autoregressive models, and diffusion models. You will build a strong foundation, understanding the unique architectures and training strategies for each, and compare essential frameworks like PyTorch and TensorFlow.

Core generative models and techniques
本课程是 Microsoft Generative AI Engineering 专业证书 的一部分

位教师: Microsoft
包含在 中
了解更多
推荐体验
推荐体验
中级
This program is for developers with foundational Azure & Python skills, seeking to build & customize generative AI models in the Microsoft ecosystem.
推荐体验
推荐体验
中级
This program is for developers with foundational Azure & Python skills, seeking to build & customize generative AI models in the Microsoft ecosystem.
您将获得的技能
要了解的详细信息

添加到您的领英档案
January 2026
23 项作业
了解顶级公司的员工如何掌握热门技能

积累 Software Development 领域的专业知识
- 向行业专家学习新概念
- 获得对主题或工具的基础理解
- 通过实践项目培养工作相关技能
- 通过 Microsoft 获得可共享的职业证书

该课程共有4个模块
This foundational module introduces the diverse landscape of core generative models beyond LLMs. You will explore the distinct architectures and principles behind Generative Adversarial Networks (GANs), autoregressive models, and diffusion models. You will also dive into the practical aspects of model creation by comparing essential training frameworks like PyTorch and TensorFlow and learning the fundamental strategies for training these powerful models on Azure. Important Notice on the Azure Interface: The screencast videos and screenshots were last updated in late 2025. Please be aware that Microsoft may have updated the Azure interface since then. If the steps shown in the course materials look different from your current Azure environment, please follow the most up-to-date interface, as the underlying concepts and learning objectives remain the same.
涵盖的内容
6个视频7篇阅读材料6个作业
6个视频•总计27分钟
- Introduction to Microsoft Generative AI Engineering certification•4分钟
- Introduction to core generative models and techniques course•3分钟
- Core models in generative AI•4分钟
- Visualizing model outputs: GANs, Autoregressive, and Diffusion•7分钟
- Using a pre-trained model in Azure AI Foundry•5分钟
- Module 1 summary: From core theories to training fundamentals•3分钟
7篇阅读材料•总计80分钟
- Course syllabus and recommended background•5分钟
- Exploring GANs, Autoregressive, and Diffusion models•20分钟
- Introduction to Model Parameters•10分钟
- Insights on model functionality•10分钟
- Introduction to training libraries and strategies•15分钟
- Analyzing training challenges and strategies•10分钟
- Choosing the right model and framework: a case study•10分钟
6个作业•总计210分钟
- A tour of generative models: First encounters•30分钟
- Controlling the output: A parameter tuning activity•30分钟
- Core generative models quiz: Practice Quiz•30分钟
- Applying model training and evaluation strategies•60分钟
- Training strategies assessment: Practice Quiz•30分钟
- Module 1 evaluation: Graded Quiz•30分钟
This module provides a deep dive into autoregressive models, the engines behind sequential data generation. You will focus on their application in tasks like time-series forecasting and text generation. Starting with the basic principles of next-token prediction, you will use Azure AI Foundry to implement models like TimeGEN-1. You will then advance to sophisticated techniques for controlling model output, ensuring your generated sequences are both coherent and high-quality. Important Notice on the Azure Interface: The screencast videos and screenshots were last updated in late 2025. Please be aware that Microsoft may have updated the Azure interface since then. If the steps shown in the course materials look different from your current Azure environment, please follow the most up-to-date interface, as the underlying concepts and learning objectives remain the same.
涵盖的内容
5个视频6篇阅读材料5个作业
5个视频•总计16分钟
- Mastering sequential data with autoregressive models•3分钟
- Sequential data with autoregressive models•4分钟
- A first look at generating sequences in Azure AI Foundry•3分钟
- Advanced techniques in sequential modeling•3分钟
- Module 2 summary: From next-token prediction to advanced forecasting•2分钟
6篇阅读材料•总计65分钟
- Autoregressive model techniques•10分钟
- Autoregressive models in practice•10分钟
- Exploring advanced sequential methods•15分钟
- Tradeoffs in advanced sequential modeling techniques•10分钟
- From Prototype to Production: Optimizing Sequential Models•10分钟
- Case study: building a production-ready forecasting system•10分钟
5个作业•总计210分钟
- Basic sequential data generation•60分钟
- Autoregressive model skills: Practice Quiz•30分钟
- Implement autoregressive model techniques for sequential tasks•60分钟
- Advanced sequential assessment: Practice Quiz•30分钟
- Module 2 evaluation: Graded Quiz•30分钟
This module focuses on the cutting-edge technology of diffusion models for creating and editing stunning, high-fidelity images for any purpose. You will learn the fundamental "denoising" process that allows these models to generate photorealistic visuals—from creative compositions to professional graphics—using simple text prompts. You will then move beyond basic generation to master advanced techniques like inpainting, outpainting, and using negative prompts to gain precise control over your visual outputs. This will equip you to produce tailored, high-quality images for a wide array of business and creative applications. Important Notice on the Azure Interface: The screencast videos and screenshots were last updated in late 2025. Please be aware that Microsoft may have updated the Azure interface since then. If the steps shown in the course materials look different from your current Azure environment, please follow the most up-to-date interface, as the underlying concepts and learning objectives remain the same.
涵盖的内容
5个视频5篇阅读材料6个作业
5个视频•总计24分钟
- Generating images with diffusion models•3分钟
- High-fidelity image generation•6分钟
- Introduction to the image generation studio and its controls•7分钟
- Mastering image generation with diffusion•7分钟
- Module 3 summary: From basic prompts to precise artistic control•2分钟
5篇阅读材料•总计60分钟
- Diffusion model fundamentals•15分钟
- Diffusion models in image generation•10分钟
- Advanced diffusion strategies•15分钟
- Analyzing diffusion model outcomes•10分钟
- A creative workflow: Analyzing the master image lab•10分钟
6个作业•总计220分钟
- Generating and refining images with diffusion models•60分钟
- Diffusion model skills quiz: Practice Quiz•30分钟
- Advanced image editing: Inpainting and Outpainting•30分钟
- Combining diffusion techniques for a master image•40分钟
- Advanced diffusion skills evaluation: Practice Quiz•30分钟
- Module 3 evaluation: Graded Quiz•30分钟
In this final module, we pivot from code-centric development to a powerful, high-level approach for accelerating model creation. You will master Azure ML Designer, a visual, drag-and-drop environment for rapid prototyping and pipeline development. You will learn to construct, train, evaluate, and prepare sophisticated models for deployment without writing extensive code. This module equips you with essential MLOps skills, enabling you to build and manage the entire machine learning lifecycle efficiently. Important Notice on the Azure Interface: The screencast videos and screenshots were last updated in late 2025. Please be aware that Microsoft may have updated the Azure interface since then. If the steps shown in the course materials look different from your current Azure environment, please follow the most up-to-date interface, as the underlying concepts and learning objectives remain the same.
涵盖的内容
6个视频6篇阅读材料6个作业
6个视频•总计24分钟
- From prototype to pipeline with Azure ML Designer•3分钟
- Prototyping with Azure ML Designer•4分钟
- A guided tour of the Azure ML Designer interface•5分钟
- Evaluating advanced prototypes•6分钟
- Module 4 summary: From visual prototyping to evaluated pipelines•2分钟
- Course summary: Your journey through generative models and techniques•4分钟
6篇阅读材料•总计65分钟
- The power of visual prototyping•10分钟
- Effective prototyping techniques•10分钟
- Anatomy of a designer pipeline•10分钟
- From prototyping to deployment•15分钟
- Continual improvement in model design•10分钟
- Bridging the gap: from visual design to custom code•10分钟
6个作业•总计235分钟
- Building your first pipeline in Azure ML Designer•45分钟
- Creating model prototypes•40分钟
- Low code prototyping skills: Practice Quiz•30分钟
- From prototype to production: Deploying a designer pipeline•60分钟
- Advanced development skills: Practice Quiz•30分钟
- Module 4 evaluation: Graded Quiz•30分钟
获得职业证书
将此证书添加到您的 LinkedIn 个人资料、简历或履历中。在社交媒体和绩效考核中分享。
位教师

提供方

提供方

Our goal at Microsoft is to empower every individual and organization on the planet to achieve more. In this next revolution of digital transformation, growth is being driven by technology. Our integrated cloud approach creates an unmatched platform for digital transformation. We address the real-world needs of customers by seamlessly integrating Microsoft 365, Dynamics 365, LinkedIn, GitHub, Microsoft Power Platform, and Azure to unlock business value for every organization—from large enterprises to family-run businesses. The backbone and foundation of this is Azure.
从 Software Development 浏览更多内容
SSimplilearn
课程

课程
PPearson
专项课程
人们为什么选择 Coursera 来帮助自己实现职业发展

Felipe M.

Jennifer J.

Larry W.

Chaitanya A.
常见问题
To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.
When you enroll in the course, you get access to all of the courses in the Certificate, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.
更多问题
提供助学金,




