Microsoft Build 2022 – Community Ninjas review

by Contributed | Jun 5, 2022 | Technology

This article is contributed. See the original author and article here.

Hi ninjas and guest,

If you expect me to go straight to a technical overview of what was good and what could be better, then you are probably not following me here.
Anyone who is familiar with the Community Ninjas blog, already knows that we love the stories of the community, we like to meet the people behind the stories, we like to bring the community aspects of the technical events, so it’s clear that we could not skip the stories from the Microsoft’s largest annual conference,

The Microsoft Build!

Obviously you can always scroll down to the next story.

So, let’s start with the story behind this post, followed by the stories of the community.

What is Microsoft Build (from my perspective)?

According to Wikipedia Microsoft Build is an annual conference event held by Microsoft, aimed at software engineers and web developers… “aimed developers” is what I remembered, but if you are database administrator or just working with SQL Server, then this year was a bit different. SQL Server 2022 public beta was released and first announced. The SQL Server team presented multiple sessions showing some of the new features everyone can now examine. If you remember for example, then SQL Server 2019 was released during the Ignite conference which more fit for such.

Covid-19 is still here! In the Third time the Microsoft Build conference runs virtually. Many people did not like, since they miss the in-person meeting. I, on the other hand, actually liked it a lot. Microsoft Build, like other Microsoft global events, are usually held in the USA. I am pretty sure that I could not travel to USA at this time and I know that many people have the same limitation – probably most of the global community. Having a virtual event has a lot of advantages. A virtual event increases accessibility both in terms of distance, for people who are on the other side of the world and also in terms of physical accessibility for people with disabilities. With that said, I understand the other side as well. Yes, it much better to meet in-person, but it is better to meet virtually than none. I am wondering how many prefer a virtual conference, on-premises, or maybe hybrid. What do you prefer, why?

The story behind this post

The original plan before the conference

A few days before the conference, I had an idea – let’s get some reviews from the community and publish it in the Microsoft Community Ninjas Blog. My original plan was to find some ninjas from the community who could provide an overview of the event from their point of view. I intended to collect the reviews and publish it in a single post a few days after the conference end. Originally the plan was to get 2 to 4 short paragraphs from each.

The first step was to create a registration form for those who want to review the event. Next published our Microsoft Build 2022 – Call for writers/reviewers in several social media networks including the Community Ninjas group on Facebook.

As always, the response was great and many members of the community responded to the call.

Out of the submitted responses we selected Six members for the task.

The next steps after the event

I probably did not explain the original plan well, or maybe we chose an amazing team with capabilities and experience I did not take into account. A day before the event I spoke with Carina Claesson, one of the reviewers. Carina sent me a number of links to posts she had previously published which included an overview of events. I immediately realized that what I was about to receive from Carina was much more than I had originally intended – She has written amazing reviews in the past and I started to realize that if I am going to get such a review here, then it is not something that can be assimilated in a single post but something that must stand on its own.

I asked the staff to provide the review no later than one week after the event end. One day more or less and I had all the reviews. It turnup that Carina was not the only one who provide such great work.

Something in my original plan was not best option.

I scheduled a meeting with all the team to come up with a better plan.

The reviewers team

Before I introduce all of our team members, I would like to take this opportunity to thank everyone who took part in this small project. We did not have much time from the moment the idea came up to the beginning of the event and the need to implement the task, and in less than a week we had to coordinate, divide tasks, and bring the best reviews there have been to the Microsoft BUILD conference. Here are the reviewers behind the project

What are we planning

next weeks?

Instead of reviewing the event in a single post, we decided that we had enough stories for an entire book, so we will publish a series of Build conference reviews. In the next coming days for a few weeks we will publish more posts in which we will present overview from speakers, attendees, Microsoft employees and community members.

This post will be the opening of the Microsoft Build community reviews.

I will present general insights from several members of the community including a short summarize from the reviewers team. 

next year?

This experience thought me a so much and we already spoke about huge plans for next year. The sky’s NOT the limit as we touch the Azure clouds every day 

First of all, I would like to work together with the build event team, and run a similar project as we did this year with their support. I want to take it to the next level.

I am assuming that next year the event will be held in-person (physical) or as hybrid event. Therefore, like any big newspaper, I want to send reviewers to the field, participate physically in the event (on-premises) to do the task. The reviewers will be able to go around and interview the speakers, the organizers of the event and the attendees in person, take some pictures and bring back their and the community insights.

For the purpose of the assignment we prepared for each of our reviewers this year, a certificate which identifies him as an official reviewer of of the Microsoft Community Ninjas.

So… let’s go over the Microsoft build event from registration to closing as seen from my eyes, my thought, and my insights…

Registration and schedule

The interface is awesome! This is the same system which was used last year. We need such system for our local conferences like in sqlsaturday. It’s simple to use and powerful to manage.

BUT REMEMBER TO TURN DOWN YOUR SPEAKERS!

you have been warned 

It’s a real party!

The music is loud and rhythmic. Lots of fun and lots of noise. I’m not sure anyone took into account that some of us are not in the US and we could be in the middle of the night. The music is turned on by default and you will be able to wake up not only your children but also the neighbors.

After a few hours of listening I started to go crazy from the background music that was running all the time in all the sessions while the lecturer was talking – very annoying. My recommendation is not to leave the main page open while you go to a session. My mistake was that I opened each session in separate tab in the browser.

Awesome tool!

I love to open my schedule on the right and select the session at the same time. Unfortunately the sessions on the right panel did not refreshed automatically when I picked another session. This can be improved (assuming the issue is not in the client side).

Tip! How to select the sessions: My solution was first to filter by category “DATA”, next “Power Platform” and next “Azure”. I selected as much sessions as I can filling my calendar. Finally, I filtered by speakers to make sure that I did not miss any important session. For example, I cannot miss any session with Bob Ward. He is simply too good.

A “HUGE” ISSUE!

problem! I did not find any option to configure my user at the event as an MVP . I search for a way to link my event account to my MVP account. I assume that the way to do it was to contact the MVP team. At first glance this seems irrelevant, but when I signed up for one of the Round Table sessions, my nomination was declined. This seems very strange to me in light of the fact that this was a discussion directly related to my MVP field. What’s more, I know the lecturer and we even schedule for him to speak in the User Group which I lead. He knows me by name, so it does not seem that the filtering goes through the speakers themselves. I contacted the speaker after the session and his words were “this is strange”. I agree. I missed a meeting where I could contribute to.

Sessions level & speakers

Round table sessions were too short. We had a great discussion and 30min was just not enough. The Round tables sessions are awesome!

I participate in all the sessions my schedule allowed me, moving from one session to the next. This event is a pure enjoyment. I am not sure id I learned anything new, but this is a result of the fact that I follow the updates in close channels. Anyone whom I spoke to described it as a  pure learning event.

If I need to highlight two best sessions then this will be one of them: a Round Table with Rohit Nayak and Thomas Weiss:

The only problem was that all participates and the speakers wanted to continue and the time was too short.

And obviously the session of the SQL Server team will be in the top but really too short to learn anything. nice for announcements and for new users mostly.

Between the sessions

The only thing I was really missing during the whole event, is the interaction between the participants during the session and between the sessions. The use of chat is technologically efficient, but outdated. I expect virtual events of this magnitude to activate more attractive tools such as virtual reality. The interface of the event was very efficient and convenient and there were no issues. I remember last year there were many technical problems during the first day of the event and I even missed one session altogether since I could not connect to. This year I did not noticed or heard about any issue.

After event

It is highly recommend to watch the sessions which you missed and these you want to dive into. Continue your learning journey beyond the Microsoft Build. You can connect with experts and technical communities. Ask the Expert on topics that you loved at Microsoft Build, use the Microsoft forums for technical questions and the social media networks to interact and meet the experts. Join live meetups and user group’s meetings in your region and local language. Continue your learning now.

Microsoft New Documents

At the first day of the event, a significant amount of new documents were published to support all the new features, new products and new services which were announced at the Microsoft Build conference. If you participate in the Microsoft Build 2022 event or if you missed it, you still need to follow the new documentation of the products/service which you want to use. 

Check the (almost) full list of documents in this post!

A brief overview from speakers, attendees, Microsoft employees and community members

Sray Agarwal – Microsoft MVP and Build event speaker

I attended Microsoft Build 2022 in-person for the first time. I have been an audience to Build before but that was virtual. I was very keen on attending this one and jumped on the opportunity as soon as I got an invitation. Being an MVP, I always wanted to disseminate my experience to a larger community, and nothing can be bigger and better than Build. This build was special for two reason – first as it was a hybrid conference and second as I was a speaker on the topic, I am passionate about. I spoke on responsible and ethical AI and the most exciting part of my session was a room full of audience. Interestingly, the audience were just not listener but very interactive, I was glad about the kind of questions and perspective I got from my audience. The entire build session this year was designed that will allow people to attend and participate in the session from either comfort of their home or from the venue. What I like was the mix of speakers, almost all session was designed in a way that it was very informative and insightful for technical and non-technical experts. This time the audience comprised of people who are in university to people who are stalwarts in their field of expertise. The technical sessions were very insightful. They revealed newer ways of implementation, newer ways of integration and newer way of looking at things. I just wish that we had more time for audience interaction post our sessions.

Based out of London, Sray Agarwal is conversant in advanced Machine Learning with profound knowledge of algorithms and advanced statistic, Sray has joined us as a Principal Consultant in the Fractal AI. His contribution to the development of the technology was recognised by Microsoft when he won the Most Valued Professional in AI award in 2020 and 2021. He is also an expert for United Nations (UNCEFACT) and have recently authored a book on Responsible AI published by Springer

Rajkumar Jain, Cloud Solution architect and DevOps architect and community blogger.

Hello friends/readers,

AWESOME, AMAZING, WOW

I would like to start with these three words about Microsoft Build event.

Most awaited event for cloud community held by Microsoft CEO today. I am very excited to join and listen about new announcement, enhancement and upcoming future driven technology.

CEO shared multiple innovative ideas, use cases and how developer can optimize their efforts towards development. That’s why techno expert was waiting to unfold 2022 Microsoft box, excited to join and listen announcement to build future driven application and tools using cloud services.

Let me share summary of event

Session was divided into 10 innovative ideas of Azure growth that will cloud community to grow few of them are available and few of them will release soon.

CEO explain how Azure Developer flow help to grow and optimize the development in hybrid model.

Github used as SCM tool and enhanced feature can be used as DevOps/DevSecOps

CodeSpace – A tool use for developing cloud native application

Dev Box – Multi device support either it is IOS device, android device, Linux device or Windows device

Github Copilot – This is community tool where lots of community provider helping to groom Github project and have limited access to only community builder. Very soon it will be available for general availability.

Azure + 5G – Make a difference in society

Azure orbital – Help space agency to grow using Azure orbital service

Window 11 – Microsoft store

Windows 365 – Replace local pc with cloud pc in one click

Xbox Cloud Gaming – available in 26 countries

Cloud native app – All application develops on Microservices

Azure Container Apps – Build modern apps on open source, Focus on apps not on infrastructure

Azure Kubernetes Service (AKS) – Fully managed Kubernetes is the cloud , seamless DevOps

Azure Confidential Computing  – Data in use , Data in rest and Data in Transit                      

New Announcement – Microsoft store Ads, sharing 100% revenue, Azure cognitive services

Many more to come in future for Developer / Business community to grow and achieve goal at minimum cost , minimum time and optimized infra resource.

I hope you like my review , this year I attend virtually but may be next year we will meet in person as you know currently world is working in Hybrid mode :smiling_face_with_smiling_eyes:.

Stay Safe Stay Healthy.

Thanks

Rajkumar Jain

Mohamed El-Qassas & Heba Kamal, the first MVP couple in Middle East and Africa

As expected from the first MVP couple in Middle East and Africa, Mohamed and Heba decided to review the Microsoft Build conference together and wow, what a nice job they have done. They prepared a comprehensive overview of several pages with pictures and insights. We will publish their review in a separate post in a few days. 

When I asked then yo provide one sentence in a nutshell, they confirm that Microsoft Build 2022 was a well-organized and successful digital event as usual, and in this post, we have tried to cover most of the important updates and announcements that were shown in Microsoft Build by the CEO Satya Nadella, and it was a really helpful keynote that covered incredible and fantastic announcements and updates.

keep following the Microsoft Build series of reviews to read their review!

Kamlesh Kumar, Integration Architect, Technical Writer and co-leader in the Microsoft Community Ninjas

Overall, how the event was valuable to you and how was it valuable to the community

>> First of all I would like to thanks Microsoft and team to organize this build event. As expected we got to know the many new features and roadmap for many products that Microsoft has planned. This event was very much informative and to know the products upcoming features. If I talk about the community prospective then this build event was not only for Tech person though the non-tech person can also get a lot of new information and if they want to learn the technical stuff then from base they can start.

What do you think is the target audience for this event

>> Personally I feel, this event was for all, either you are techie person or non-technical person who want to learn.

How valuable (for you/for the community) was the content of the lectures you heard?

>> Content of lectures and session was very informative and I learned the many things with live demo given by team.

Do you think that the event provided an opportunity to connect with experts? How?

>> Yes, obesely. There was an option to connect with expert from all over the world in different different time zones. There was an option to connect with experts or product group in one-one conversion and get the expertise advice from them about the product or in their expertise area.

What do you think about the way the event was organized (connection, content, administrative, the web interface, and so on) and what could  be done better next year

>> Personally I feel it was very nice and well organized in all the area but still i was missing the old day where we can directly connect with experts in person and discuss the topics. I personally loved the connection zone and learn area in this build and I would love to see much more in future in these areas.

Carina M. Claesson, Microsoft Business Applications MVP

Do you remember how I stated this long (very very very long) post? Remember how my original plan changed once I got the reviews which Carina wrote?

Well… Carina wrote a full book, and not a short one. in the following days Carina is going to publish not one and not two reviews, but at least 5 separate posts, each better than the other. In the meantime, here are some insights from our top reviewer of the Microsoft Build conference 2022.

1. Overall, how the event was valuable to you and how was it valuable to the community
I like to keep myself updated around the roadmap for the technologies I’m working with, so that I can suggest good solutions for my customers. I work with Microsoft Business Applications and Power Platform is a part of this event. There are Release Waves and new features documented in Release Plans and there are Microsoft events, where big announcements are made, and the Release Plans might be updated. The event is valuable for the community because Build invites the community to participate and connect.
2. What do you think is the target audience for this event
There is already an answer to this question on the Build website, in the FAQ. There it says it is for developers, engineers, and IT professionals, students and career changers new to the tech industry. If you ask me, I would say traditionally it has been targeting professional developers, for the past years low code and collaboration features have been included too. Target audience today I would say professional developers working with Microsoft technologies, but also anyone who creates solutions with Microsoft Business Applications, anyone who utilizes and guides others within the collaboration features in Microsoft 365, and of course anyone who wants to start a career within the already mentioned areas.
3. How valuable (for you/for the community) was the content of the lectures you heard?
As already mentioned, Build often comes with big announcements. Within Microsoft Business Applications two such big announcements were Power Pages (Power Apps portals reimagined) and Express Design (making it possible to go from an image or Figma design to app). Besides of now knowing that we have more possibilities within the platform, at Build we could also see some demos using it in action.
4. Do you think that the event provided an opportunity to connect with experts? How?
Yes, by participating and engaging in the chat during the sessions and by connecting with others who also attended the event. For the lucky people who got to attend in-person at one of the regional spotlights, that meant even more opportunities.
5. What do you think about the way the event was organized (connection, content, administrative, the web interface, and so on) and what could be done better next year
Really good with the choice to participate virtually or at one of the regional spotlights. The digital venue had lots of different choices for languages, closed captioning and audio tracks, and sign language to be turned on or off. It was perfect with a digital backpack and being able to save sessions for up to 90 days. If I could wish for something more, it would be to have sessions available on-demand even faster and that it was possible to download the presentation decks from all sessions (I’ve seen it for some only). Overall, Build 2022 was a really great and inspiring event!

when one door closes another one opens

Wow, it’s time to close the day and prepare the next post in the Microsoft Build 2022 series – Community Ninjas review.

I hope you enjoyed reading and that the content was not too long. Did you cheat and scroll down to skip some sections? We invite you to add your review and feedback using the comments below

Thanks for joining us in the first review of the Microsoft Build conference 2022

Azure Cognitive Services Hands-on Workshop resources and insights.

by Contributed | Jun 4, 2022 | Technology

This article is contributed. See the original author and article here.

Agenda

The agenda of the workshop was to provide students with a hands-on experience of Microsoft Azure Cognitive Services focusing mainly on Custom Vision and QnA Maker.

Also provided a brief introduction to Microsoft Azure and fundamentals of cloud computing concepts. Help them figure out how to exhibit Artificial Intelligence, Machine Learning, and Natural Language Processing (NLP) projects on their resume.

Overview

The workshop was attended by 30 students. All students received a Microsoft Azure for Student subscriptions.

Starting with the basic concepts of cloud computing and how Azure Cognitive Services fits into the Microsoft Azure ecosystem. Elaborating on how API calls embed the ability to see, hear, speak, search, understand, and accelerate advanced decision-making into modern applications.

Quick revision of services under the Cognitive Services umbrella such as:

• 
  

  Question Answering – Distill information into easy-to-navigate questions and answers.

  
  


• 
  

  Conversational language understanding – Enable your apps to interact with users through natural language.

  
  


• 
  

  Speech to Text – Transcribe audible speech into readable, searchable text.

  
  


• 
  

  Computer Vision – Analyze content in images and video.

  
  


• 
  

  Custom Vision – Customize image recognition to fit your business needs.

  
  


• 
  

  Face API – Detect and identify people and emotions in images.

  
  

Flow of the workshop

After the introduction, the subscription were created by the students. Activating Azure for Student provided each of the students with a balance of $100 USD that they could use to explore and experiment with the services on the Azure portal.

All the activities performed were strictly directed by the Learning module on Microsoft Learn

Custom Vision

Note

---

Click the Custom Vision title to view the Microsoft Learn Document for this activity.

The first activity to be performed was on Custom Vision, where we discussed:

• 
  

  What is Custom Vision?

  
  


• 
  

  What are the applications of custom vision?

  
  


• 
  

  How to implement Custom Vision to your application?

  
  
  
  
  1. Creating a Custom Vision resource to get started
  
  
  2. Select the subscription, resource group, region, name, and pricing tier
  
  
  3. Upload the existing images of an object to train the model.
  
  
  4. Select the “Quick Training” option to quickly prepare the model in minutes
  
  
  5. Train an image classification model based on existing images
  
  
  6. Publish the model to use it in your applications
  
  
  
  


• 
  

  How to verify the functionalities of the trained model?

  
  

  To verify and test the model by running a simple command-line program in the Cloud Shell, real-world solutions, such as web sites or phone applications, use the same ideas and functionalities.

  
  


• 
  

  Troubleshooting the errors and blockades faced by the attendees throughout the workshop

  
  

After the Custom Vision session, there was short FAQ session to answer all the queries regarding custom vision.

QnA Maker

Note

---

Click the QnA Maker title to view the Microsoft Learn Document for this activity.

In the QnA Maker session, we aimed to create a live chat bot using python by:

• Understanding what are Chat-bots


• What are the applications for Chat-bots


• Create a chat-bot
  
  
  
  1. Creating a QnA Maker resource to get started
  
  
  2. Select the subscription, resource group, region, name, and pricing tier
  
  
  3. Create a custom question answering knowledge base
  
  
  4. Edit the knowledge base
  
  
  5. Train and test the knowledge base
  
  
  6. Create a bot for the knowledge base
  
  
  7. Test the bot to verify its functionalities.
  
  
  
  

Conclusion

A questioning session was held where students can ask their queries about Microsoft services especially regrading Microsoft Azure and its services. A brief discussion about the Microsoft certifications and how students can leverage Microsoft Learn to excel in the certification exams.

Provision of a roadmap on what their approach should be if they want to make a career in Artificial Intelligence, Data Science, and Cloud Computing.

Take away from this session was to get a hands-on experience on Custom Vision and QnA Maker as service offerings from Microsoft Azure, and build real-time project on the same to showcase on their resume.

Active Learning at scale, with Azure SQL and Azure ML

by Contributed | Jun 3, 2022 | Technology

This article is contributed. See the original author and article here.

 Figure 1: Example demonstration of the value of storing model inference results in Azure SQL DB. We performed a query to retrieve a video frame that shows young Fred (FI) with his mother Fifi (FF) and close family members.

Introduction

Organizations often sit on a treasure trove of unstructured data, without the ability to derive insights from the data.

We experienced this situation while working on a co-innovation project with the Jane Goodall Institute (JGI), MediaValet, and the University of Oxford. JGI had digitized and uploaded many decades of videos of chimpanzees in the wild and wanted to enable primate researchers to use this data for quantitative scientific analyses. To this end, we built a no-code active learning solution for training state-of-the-art computer vision models. This solution allows researchers at JGI to index and understand their unstructured data assets, it allows them to join them the unstructured data with other, structured data sources, eventually enabling statistical analysis for scientific enquiries. For example, how does the social network structure change over the first few months after a new chimp was born?

In this blog post, we provide an overview of the use case, challenges, and solutions. Briefly, to enable active learning at scale, we implemented PyTorch dataset classes, which load image data from Azure Blob Storage and annotations from an Azure SQL database. Model predictions are written to the same database. The Azure SQL database can then be used for gaining new insights, using quantitative analytics (see Figure 1).

Challenges

We faced several challenges while working on this project. The largest challenge was that there is only one person in the world who can reliably recognize the over 300 individual chimpanzees by name: the famous wildlife cinematographer and scientific advisor Bill Wallauer. Over the course of several years, he spent many months living in the Gombe National Park, filming chimpanzees in the wild.

The second challenge was the sheer scale of the project. We had to store annotations for over 30 million video frames in such a way that they could be used for machine learning. At the same time, the annotations needed to be accessible to primate researchers, to enable scientific inquiry.

The third challenge was to build a no-code solution that would allow JGI staff to annotate and train deep learning models without requiring expertise in computer programming and machine learning.

Minimizing data labeling costs with active learning

To address the challenge that only Bill Wallauer can reliably recognize the over 300 individual chimpanzees by name, we needed to build a no-code solution that would maximize the returns on every data label he provides. That is, the brute-force approach of crowd-sourcing data labeling, to get as much labeled data as possible couldn’t be applied here.

Active learning is a machine learning technique that tries to minimize required labeling efforts by strategically selecting those samples for annotation that are expected to benefit the model the most. In this context, the goal is to find an optimal policy of selecting samples for annotation to maximally increase model performance on a validation set. Active learning is a relatively new technique in machine learning, and we will cover this and related topics in depth in future blog posts.

Azure SQL Server and Database enable active learning at scale

Another challenge we faced was the large scale of the project. We had to find a way to efficiently store data annotations, so that they could be used for model training, inference, and allow primate researchers to perform quantitative analysis.

A common approach to training deep learning models is to store annotations in JSON format or CSV files, for the annotations to be loaded into host memory at the beginning of training. We quickly reached limitations in terms of speed and memory usage with this approach. There are several workarounds for more advanced use cases. We decided to use Azure SQL DB for this project, which immediately alleviated all concerns around increases the dataset size. There are some very real advantages to using Azure SQL DB for a project of this scale:

• Memory limitations on the training host machines used for model training and inference are no longer an issue because there is no requirement to load the annotations for the entire dataset into memory


• Speed! We found that our implementation scaled extremely well as the dataset grew, because Azure SQL DB had no issues handling a dataset of this size.

Finally, the same SQL database we are using for training and inference can also be used by primate researchers for quantitative analytics.

Azure ML enables the automation of model training and monitoring

It was our explicit goal to build a no-code solution that would empower JGI staff and volunteers, without requiring expertise in computer programming and machine learning. We were able to achieve this goal via a set of Azure ML Pipelines, with triggers for automatic execution in response to well-defined events. These pipelines automate data ingestion, model training and re-training, monitoring for model and data drift, batch inference, and active learning.

Other Applications

Here we demonstrate how to use Azure SQL database and Azure ML to enable active learning at scale for a particular use case, but the same principles can be applied to a wide variety of applications, which can be found across industries:

• Worker Safety. Supervisors have the suspicion that a particular kind of worker behavior leads to accidents. They have a very large repository of video footage and records of work accidents. They would like to investigate whether they can find evidence in these videos that certain kinds of behaviors have indeed historically led to accidents.


• Public Safety. Public employees suspect that a particular type of traffic intersection is associated with an increased number of traffic accidents. Employees have historical GIS data on traffic accidents and footage of traffic cameras. They train a model on categorizing intersections and join that data with GIS data on traffic accidents.


• Manufacturing. A manufacturer suspects that a particular kind of manufacturing defect leads to warranty claims later. The manufacturer has a large dataset of images from manufacturing pipelines. Investigators train a model to recognize the anomaly and join the data with warranty claims to test their hypothesis. Based on their findings, they can start a product recall to avoid costly warranty claims.


• Predictive Maintenance. Acoustic sensor data on manufacturing machines are hoped to provide a signal that is predictive of outages and other equipment failure. Operators would like to know whether it is possible to join this unstructured acoustic data with maintenance records to perform predictive maintenance.

Related Tools and Services

Azure ML Data Labeling. Data Labeling in Azure Machine Learning offers a powerful web interface within Azure ML Studio that allows users to create, manage, and monitor labeling projects. To increase productivity and to decrease costs for a given project, users can take advantage of the ML-assisted labeling feature, which uses Azure ML Automated ML computer vision models under the hood. However, in contrast to the approach described here, Azure ML Data Labeling does not support active learning.

Azure Custom Vision service is a mature and convenient managed service that allows customers to label data and to train and deploy computer vision models. In contrast to the approach discussed here, the focus is on developing a performant model, rather than understanding and indexing very large amounts of unstructured data. Like the Azure ML Data Labeling tool above, it does not have support for active learning.

Video Indexer is a powerful managed service for indexing large assets of video data. It currently offers only limited options for customizing models to understand the subject domain of the dataset at hand. It also does not offer a straightforward approach to use the generated index for secondary analysis.

Conclusion

This blog post represents the first of a series of blog posts on combining Azure SQL Database and Azure ML to index and understand very large repositories of unstructured data. Future blog posts will offer more depth on the topics touched upon above. For example:

• Writing a PyTorach Dataset class for SQL


• Implementing Active Learning at scale with SQL DB and Azure ML


• Optimizing SQL tables and queries to increase training and inference speed


• Ensuring AI fairness


• Gaining scientific insights after all unstructured data has been indexed

We also welcome requests in the comment section, for other topics you would like us to cover in these future blog posts.