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 ofMicrosoft Azure Cognitive Servicesfocusing mainly onCustom VisionandQnA Maker.
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.
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 onMicrosoft Learn
How to implement Custom Vision to your application?
Creating a Custom Vision resource to get started
Select the subscription, resource group, region, name, and pricing tier
Upload the existing images of an object to train the model.
Select the“Quick Training”option to quickly prepare the model in minutes
Train an image classification model based on existing images
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.
Select the subscription, resource group, region, name, and pricing tier
Create a custom question answering knowledge base
Edit the knowledge base
Train and test the knowledge base
Create a bot for the knowledge base
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.
This article is contributed. See the original author and article here.
CISA has released an Industrial Controls Systems Advisory (ICSA) detailing vulnerabilities affecting versions of the Dominion Voting Systems Democracy Suite ImageCast X, which is an in-person voting system used to allow voters to mark their ballot.
Exploitation of these vulnerabilities would require physical access to individual ImageCast X devices, access to the Election Management System (EMS), or the ability to modify files before they are uploaded to ImageCast X devices. Jurisdictions can prevent and/or detect the exploitation of these vulnerabilities by diligently applying the mitigations recommended in ICSA-22-154A, including technical, physical, and operational controls that limit unauthorized access or manipulation of voting systems. Many of these mitigations are already typically standard practice in jurisdictions where these devices are in use and can be enhanced to further guard against exploitation of these vulnerabilities.
While these vulnerabilities present risks that should be mitigated as soon as possible, CISA has no evidence that these vulnerabilities have been exploited in any elections.
This article is contributed. See the original author and article here.
Atlassian has released new Confluence Server and Data Center versions to address remote code execution vulnerability CVE-2022-26134 affecting these products. An unauthenticated remote attacker could exploit this vulnerability to execute code remotely. Atlassian reports that there is known exploitation of tmhis vulnerability..
Note: per BOD 22-01 Catalog of Known Exploited Vulnerabilities, federal agencies are required to immediately block all internet traffic to and from Atlassian’s Confluence Server and Data Center products AND either apply the software update to all affected instances OR remove the affected products by 5 pm ET on Monday, June 6, 2022.
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.
This article is contributed. See the original author and article here.
The Microsoft Finance and Operations (Dynamics 365) mobile app, the associated mobile platform, and related mobile workspaces are deprecated effective June 2022. Existing assets will be supported through October 2024. New mobile Finance and Operations experiences should be built in Power Apps, using virtual tables from Microsoft Power Platform to access finance and operations data.
What’s happening to the Finance and Operations (Dynamics 365) mobile workspaces?
Some of the existing mobile workspaces will be replaced. The Microsoft Dynamics 365 Project Timesheet mobile app is already available as a replacement for the Project time entry mobile workspace.
Replacement experiences are planned to be released in 2023 for the following mobile workspaces:
Expense management
Inventory on-hand
Asset management
Invoice approval
Purchase order approval
Replacement experiences are not currently planned for the remaining mobile workspaces:
Note that the Warehouse Management mobile app, which is not built on the Finance and Operations (Dynamics 365) mobile app, is not impacted by this deprecation.
What’s next
Here are some additional things we encourage you to do now that the Finance and Operations (Dynamics 365) mobile app has been deprecated.
Stop building new mobile experiences in the Finance and Operations mobile app.
Begin planning for converting your existing mobile experiences to Power Apps. You have some time before the end-of-support date, but it’s never too early to start getting ready!
This article is contributed. See the original author and article here.
Although the pandemic exposed our supply chain fragilities, there are other factors that will continue to disrupt our supply chains for the foreseeable future. Geopolitical tensions between world superpowers are forcing companies to change how they trade, source, and manufacture goods, so redesigning your supply chain networks or setting up new supply chains to gain resilience is a common theme we will continue to see over the next few years. Global economies are inching towards recession partly due to the prolonged and ongoing pandemic which will increase cost pressures on businesses, and we all know gaining resilience while reducing costs is just extremely difficult. It will require us to improve our agility and pivot and adapt to changing customer and business needs.
Increase resilience with a predictive supply chain.
Manufacture and operate sustainably with minimal waste.
Transform work with advanced warehousing and robotics.
Microsoft’s supply chain experts will also deliver the must-have insights, strategies, and frameworks for chief supply chain officers (CSCOs) and supply chain leaders to think big, make bold moves, and drive real impact within their organizations1 on June 6, 2022 at 4:00 PM Eastern Time in the Southern Hemisphere II auditorium.
We hope to catch up with you and your teams at the event. Register and attend our session (see details below) for cutting-edge thought leadership about supply chain technology solutions.
Microsoft: CSCO’s role in digitally transforming supply chains with a composable approach
With growing supply chain complexities, leaders need a clear digital transformation strategy that drives visibility across the entire value chain, improves flexibility to meet customer demands, and decreases operational costs. In this session, we will share a new approach to deploying transformative supply chain technologies bespoke to your business by adopting composable characteristics without having to replace your existing supply chain solutions. The composite architecture enables accelerated time-to-value through better interoperability and data harmonization to create a resilient supply chain.
Let’s look at some of the benefits of a composable enterprise.
Composability enables circular manufacturing to advance sustainability initiatives
It’s paramount for enterprises to operate more sustainably. Most organizations have a goal to reduce and offset carbon emissions, including Microsoft. One of the ways to operate sustainably is to drive circularity. Essentiallyinstead of throwing away goods at the end of their life, finding ways to reuse or recycle them to reduce carbon emissions. To achieve circularity, businesses can customize their enterprise resource planning (ERP) systems to orchestrate new business processes. A composable system allows you to use low code to customize them easily.
Our own Microsoft Circular Centers have a unique process to optimize warehouse routing and management system to process decommissioned servers from Microsoft datacenters. There were no reverse logistics solutions that were suitable for the circular centers out of the box. By leveraging the low code Microsoft Power Platform solutions, Dynamics 365 was extended to build a reverse logistics solution that helped reuse, resale, and recycle the decommissioned data center assets. This is one of the ways that puts Microsoft on the path to achieving its sustainability goals by 2030. The outcome of this program has exceeded expectations. Our pilot circular center has been able to reuse 83 percent of critical parts and has reduced carbon emissions by 145,000 metric tons of CO2 equivalent.
This embed requires accepting cookies from the embed’s site to view the embed. Activate the link to accept cookies and view the embedded content.
The future of business applications is composable. According to Gartner, “those that have adopted a composable approach will outpace their competition by 80 percent in the speed of new feature implementation.”2 A composable business consists of modular building blocks that can be rapidly connected and orchestratedallowing organizations to adapt operations and processes to changing market conditions, new business opportunities, and unpredictable disruptions. Composable ERP solutions are, among other things, cloud-based platforms that scale without limits, leverage a modern open system architecture to reduce implementation time, and usually incorporate low-code/no-code interfaces to improve usability and customization.
One of the companies reaping the benefits of Dynamics 365 Supply Chain Solutions is Tillamook. Tillamook County Creamery Association is a farmer-owned cooperative based in Tillamook, Oregon, founded in 1909 and owned by about 80 farming families. While best known for its cheese, it has introduced more new dairy products in the past five years than in the previous fifty. At the same time, Tillamook has expanded nationally, and its products can now be found across the United States.
To support its growth and expansion, Tillamook needed a modern solution to scale and enter new distribution and sales markets. This led them to migrate to Dynamics 365 apps for Finance and Supply Chain Management. Tillamook had just begun its ERP modernization journey when the global pandemic disrupted demand and supply almost instantly. Yet despite being live for only four months, once COVID-19 spiked demand for groceries as people ate more at home, Tillamook was able to leverage the flexibility of Dynamics 365 to adapt quickly to new business needs.
“There’s been this thing with ERP over the past few years where you avoid customizations to the software so that you can take upgrades. That’s a thing of the past with Dynamics 365. You can modify the system to meet your unique business processes, adjust the logic and configure, and it still takes the updates seamlessly. We have some unique processes here with our complex supply chain, and we’ve been able to modify the system and still take those upgrades.“Travis Pierce, Director of Information Technology, Tillamook.
Enhance visibility with digital supply chain solutions
Today, manufacturers, distributors, and retailers can use the right digital supply chain solutions to build or enhance the real-time visibility required to move from reactive decision-making to predictive and proactive decision-making. To maximize operational efficiency, product quality, and profitability, they need to unify data across order fulfillment, planning, procurement, production, inventory, warehousing, and transportation.
Supply chain leaders know that the earlier potential disruptions and constraints are identified, the more successful the measures to adapt and overcome them can be. Modern improvements in technology, such as applying AI and machine learning to complex data sets, are giving businesses the insight and agility to deploy processes and systems that generate and proactively shape customer demand. These solutions also allow companies to sync and balance supply to demand by continuously optimizing production operations and distribution networks. With real-time, end-to-end visibility across the supply chain, organizations can sense, predict, and adapt to constraints and disruptions at the earliest possible opportunity.
Take the Supply Chain Visibility Guided Tour to see how a retailer can enhance supply chain visibility using Dynamics 365. The composable architecture of Dynamics 365 enables businesses to incrementally add functional capabilities that will make their supply chains more resilient without having to replace their legacy systems.
See you at Gartner Supply Chain Symposium XPOTM 2022
Supply chains continue to evolve through the current post-pandemic shift. As they do, Microsoft is committed to empowering every person and organization on the planet to achieve more. We hope you will join us at Gartner Supply Chain Symposium XPOTM 2022 by either catching our session or engaging with one of our supply chain experts. If you are unable to attend this year but are interested in learning how to start optimizing your supply chain, you can get started with a demo today or check out our webinar Create Agile and Digital Supply Chains with Dynamics 365.
GARTNER and SUPPLY CHAIN SYMPOSIUM/XPO are registered trademarks and service marks of Gartner, Inc. and/or its affiliates in the U.S. and internationally and are used herein with permission. All rights reserved.
Recent Comments