AI Articles Weekly Series

This week’s series of AI articles is from Dinesh Asanka, an 8x Microsoft MVP in SQL Server. He has been working with SQL Server for more than 15 years, written articles and co-authored books. Dinesh is a presenter at various user groups and universities.

 

Introduction to Azure Machine Learning using Azure ML Studio

Data Cleansing in Azure Machine Learning

Prediction in Azure Machine Learning

Feature Selection in Azure Machine Learning

Data Reduction Technique: Principal Component Analysis in Azure Machine Learning

Prediction with Regression in Azure Machine Learning

Prediction with Classification in Azure Machine Learning

Comparing models in Azure Machine Learning

Cross Validation in Azure Machine Learning

Clustering in Azure Machine Learning

Tune Model Hyperparameters for Azure Machine Learning models

Time Series Anomaly Detection in Azure Machine Learning

Designing Recommender Systems in Azure Machine Learning

Language Detection in Azure Machine Learning with basic Text Analytics Techniques

Azure Machine Learning: Named Entity Recognition in Text Analytics

Filter based Feature Selection in Text Analytics

Latent Dirichlet Allocation in Text Analytics

Recommender Systems for Customer Reviews

AutoML in Azure Machine Learning

AutoML in Azure Machine Learning for Regression and Time Series

Building Ensemble Classifiers in Azure Machine Learning

 

Oct '21 Technical Events

Virtual User Group Meetings

• Sep 27: Akron AITP (https://akron-aitp.org/)
• Oct 5: ONDT (https://www.meetup.com/ohio-north-database-training/)   
• Oct 20: Hudson CodeCraft (https://www.meetup.com/hudson-codecraft/)
• Oct 21 : GLUG.Net: (https://www.meetup.com/GLUGnet/events/)
• Oct 28: Cleveland C#/VB.Net User Group (https://www.meetup.com/Cleveland-C-VB-Net-User-Group/) 

 

Virtual Conferences

• Oct 16: Northern VA Code Camp (https://novacodecamp.org/)
• Oct 19: Global AI Back Together – Cleveland (https://globalai.community/global-ai-back-together/north-america-cleveland-4472/)
• Oct 26-28: AI Dev World (https://aidevworld.com/)
• Oct 29-31: Azure Community Conference (https://azconf.dev/)
• Nov 8-12: PASS Data Community Summit (https://passdatacommunitysummit.com/)

 

Azure Custom Vision Object Detection

Computer Vision and Custom Vision are 2 subsets of services provided by Azure Cognitive Services.

 

Computer Vision: Analyze content in images.

1. OCR: Optical Character Recognition
2. Image Analysis: extracts visual features from images (objects, faces)
3. Spatial Analysis: Analyzes the presence and movement of people on a video feed and produces events that other systems can respond to.

 

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

1. Image Classification: applies label(s) to an image
2. Object Detection: returns coordinates in image where applied label(s) can be found.

 

When using the Object Detection Prediction API, the response returned from azure will be a JSON dataset using the following format.

 

    public class PredictionResponse

    {

        public string id { get; set; }

        public string project { get; set; }

        public string iteration { get; set; }

        public string created { get; set; }

        public Prediction[] predictions { get; set; }

    }

 

    public class Prediction

    {

        public string tagId { get; set; }

        public string tagName { get; set; }

        public string probability { get; set; }

        public BoundingBox boundingBox { get; set; }

    }

 

    public class BoundingBox

    {

        public string left { get; set; }

        public string top { get; set; }

        public string width { get; set; }

        public string height { get; set; }

    }

 

Each BoundingBox object in the response is represented graphically by the red boxes, as shown in the sample image below

 

 

 

In addition, listed below are some Gotcha’s to watch out for when working with Object Detection

 

1. Be sure to use the same login for https://customvision.ai as the one used for the Azure portal.

 

2. Use same "Directory" in CustomVision.ai and Azure portal.  This setting can be found in the top right corner for both Azure portal and CustomVision.ai

 

3. When training the model, you must use a minimum of 15 images for every tag.  More images with different lighting, angles, and backgrounds will produce better results.

 

4. The images types used for training must be .JPG, .PNG, or .BMP, and less than 4MB.

 

 

 

.Net Release Schedule

There has been some confusion created with the release of .Net and .Net Core releases and how their support will be impacted in the near future.  Listed below is a summary from the Microsoft Support Policy:

.NET and .NET Core refer to several technologies including the runtime, ASP.NET Core, Entity Framework Core, and more.
.NET Core and future versions of .NET provide Long Term Support (LTS) releases that get three years of patches and free support.
Patches to releases are compatible, which eliminates risk adversely affecting applications.

For details, see the .NET and .NET Core support policy.

 

Version	Original Release Date	Latest Patch Version	Patch Release Date	Support Level	End of Support
.NET 5	November 10, 2020	5.0.10	September 14, 2021	Current	6 months after .NET 6 release (around May 2022)
.NET Core 3.1	December 3, 2019	3.1.19	September 14, 2021	LTS	December 3, 2022

 

 

For better visualization of the .Net roadmap, see the timeline below for release dates of past, present, and future releases.

 

A day of data and AI

O’Reilly Radar presents a day of data and AI that will showcase what’s new, what’s important, and what’s coming in the field. It’s free and open to the public.

The event is happening October 14 and again on October 21.  It's free, but registration is required.

RSVP here for October 14, 7:00am–10:30am PT / 10:00am–1:30pm ET

RSVP here for October 21, 8:30am–12:00pm IST / 2:00pm–5:30pm AET