Firstly a big 'Thank You' for hosting a Global AI Tour stop in your local area in April or May.
Take a look at all the communities also getting involved: Global AI on Tour locations.
- Session Title: Creating an application that can see, build your own AI model
- Session Abstract: In this workshop you will be introduced to the Microsoft Azure Cognitive Services, a range of offerings you can use to infuse intelligence and machine learning into your applications without needing to build the code from scratch. We will cover pre-trained AI APIs, such as computer vision, that are accessed by REST protocol. Next, we will dive into Custom AI that uses transfer learning - Microsoft Azure Custom Vision. This enables you to provide a small amount of your own data to train an image classification model. Wrapping the workshop up by building our custom trained AI into an application - using Logic Apps, this technology is ideal for building data pipeline processes that work with your machine learning models.
- Technologies included: Azure Custom Vision, Logic Apps
- Session Title: Integrate custom skills in azure cognitive search
- Session Abstract: In this workshop you will make sense of unstructured data using AI services. You are a Tailwind Traders developer and Tailwind Traders has a lot of legacy data that they’d like to leverage in their apps. This data is from various sources, both structured and unstructured, and includes images, forms, pdf files etc. You'll learn how you can build an end-to-end architecture, with Azure Cognitive Search at its heart, to make sense of this unstructured data within the business. You’ll be introduced to AI concepts, like the ingest-enrich-explore pattern, skillsets, cognitive skills, natural language processing, computer vision, and beyond.
- Technologies included: Azure Cognitive Search, Azure Storage and Storage Explorer, Azure Cognitive Services including Forms Recognizer, Azure Functions.
- Session Title: No-code/Low-code machine learning
- Session Abstract: In this workshop you will start building machine learning models – faster than you think. Tailwind Traders uses custom machine learning models to fix their inventory issues – without changing their Software Development Life Cycle! How? Using Azure Machine Learning Visual Interface. You’ll learn about the data science process and get an introduction to Azure Machine Learning Visual Interface. You’ll see how to find, import, and prepare data, select a machine learning algorithm, train and test the model, and deploy a complete model to an API. Get the tips, best practices, and resources you and your development team need to continue your machine learning journey, build your first model, and more.
- Technologies included: Azure Machine Learning Visual Interface, Azure Machine Learning Service, Visual Studio Code, Azure Machine Learning Notebook VMs
- Session Title: Conversational AI
- Session Abstract: There is a growing demand on building conversational agents that empower human-machine interaction in natural language. Despite the proliferation of virtual personal assistants, building these agents remains to be difficult and there still remains plenty of unanswered questions and challenges. The conversational AI platform that is based on the BotFramework (BF), and uses tools of Natural Language understanding (Language Understanding Service LUIS) and dialog design (Dialog Composer), addresses many of these challenges to enable building these agents with relative ease. The goal of this workshop is to bring some of the best practices of building these conversational agents using the tools of BF and Cognitive Services. While it would be an opportunity to share some of the new and exciting features of the BF, the Dialog Composer and LUIS, we will also run through best practices that are involved in the design of systems.
- Technologies included: Bot Framework, Language Understanding Service (LUIS), Dialog Composer
- Session Title: Deep Learning from data to production
- Session Abstract: This full day workshop is designed to get attendees up to speed on the rudiments of modern machine learning at cloud scale via both theory and hands on content. The day starts with working on the foundational concepts of supervised machine learning which you will apply locally using scikit-learn and Tensorflow frameworks. After working locally, the workshop will support you in creating your first cloud machine learning experiment by utilizing Azure Machine Learning offerings. Next you will dive deeper into Azure Machine Learning advanced experimentation techniques by exploring hyperparameter tuning, automated machine learning and machine learning pipelines. Taking steps to improve your model and creating agility and ease of tracking when it comes to tuning it. Finally, the workshop will present the intersection between Data Science and DevOps. Taking your cloud model and managing its lifecycle into production and beyond. By the end of the day you will have worked on each stage of the machine learning lifecycle and explored cloud tooling that can support your bespoke machine learning projects.
All the content for the "Developers Guide to AI" Learning Path is made available for you to deliver to your local communities. There are 5 presentations with train the trainers resources and all the materials needed to setup the demos.
- AIML10: Making Sense of your Unstructured Data with AI
- (Azure Cognitive Search)
- AIML20: Using Pre-Built AI to Solve Business Challenges
- (Azure Cognitive Services + ONNX)
- AIML30: Start Building Machine Learning Models Faster than you think
- (Azure Machine Learning Designer)
- AIML40: Taking Models to the Next Level with Azure Machine Learning Best Practices
- (Azure Machine Learning Service SDK and Automated ML)
- AIML50: Machine Learning Operations - Applying DevOps to Data Science
- (Azure Machine Learning Deployment and Azure Pipelines)
Also all recordings of the sessions from Ignite Orlando 4th November - 8th November are available below:
- AIML10: https://myignite.techcommunity.microsoft.com/sessions/82986?source=sessions
- AIML20: https://myignite.techcommunity.microsoft.com/sessions/82987?source=sessions
- AIML30: https://myignite.techcommunity.microsoft.com/sessions/82993?source=sessions
- AIML40: https://myignite.techcommunity.microsoft.com/sessions/83002?source=sessions
- AIML50: https://myignite.techcommunity.microsoft.com/sessions/83003?source=sessions