Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
SlideShare a Scribd company logo

Introduction to Machine learning and Deep Learning

•
•
Nishan Aryal
Nishan Aryal

Overview of Machine Learning and Deep Learning. Brief introduction to different types of BI Reporting tools like Power BI, SSMS, Cortana, Azure ML, TenserFlow and other tools.

Related slideshows

AI Builder Deep Scottish Summit 2020
AI Builder Deep Scottish Summit 2020AI Builder Deep Scottish Summit 2020
AI Builder Deep Scottish Summit 2020
 
Microsoft AI Platform - AETHER Introduction
Microsoft AI Platform - AETHER IntroductionMicrosoft AI Platform - AETHER Introduction
Microsoft AI Platform - AETHER Introduction
 
201906 04 Overview of Automated ML June 2019
201906 04 Overview of Automated ML June 2019201906 04 Overview of Automated ML June 2019
201906 04 Overview of Automated ML June 2019
 
1 of 35
Introduction to Machine learning and Deep Learning
NISHAN ARYAL Cloud App Developer CTO – Innovation Lab “Let’s learn together and share together” is what I believe www.aryalnishan.com.np
If you invent a breakthrough in artificial intelligence, so machines can learn, that is worth 10 Microsoft
What is Machine Learning?
Introduction to Machine learning and Deep Learning
Introduction to Machine learning and Deep Learning
Introduction to Machine learning and Deep Learning
What is Machine Learning? • Using Computer Power to gain insight into data that might other be elusive • Credit Card Fraud Detection • Online Shopping recommendations • Self driving Cars and Tesla Motors • Tuning data into Solutions • Machine Learning Strategies • Supervised Learning • Unsupervised Learning
Traditional Programming Program Data Output
Machine Learning Data Output Program
Prepare Data • Import data • Pre-process data Train Model • Select Learning Algorithm and Build Model • Experiment/Iterate/Evaluate Make Operational • Prepare Model for Deployment • Deploy and call fro Applications
You have been using ML since long
Machine Learning/Deep Learning or AI?
Bing maps ships with ML Traffic Prediction Service Microsoft Kinect can watch users gestures Computers work on users behalf, filtering junk email Successful real-time speech-to-speech translation Microsoft Search Engine build with Machine Learning Enables data mining of databases MICROSOFT MACHINE LEARNING HISTORY
SQL Server Data Mining Spam filtration Gestures understanding in Microsoft Kinect Azure Machine Learning Using Data Mining in search engines Bing Maps started to use ML for traffic estimate Voice recognition Microsoft & Machine Learning 1999 201220082004 201420102005
Years of Innovation
Introduction to Machine learning and Deep Learning
Introduction to Machine learning and Deep Learning
Microsoft Azure Machine Learning  Reduced Complexity  Access Through Web Browser, no need to install any thing  Collaborate work with anyone  Visual composition, easy to use, No Coding  Good storage of Algorithm (Use in Bing search, Xbox..)  Have good support for R studio, Python and Jupyter notebook
Azure Machine Learning Solution
Azure ML Services pre-configured environment for deep learning using GPU instances Deploy in minutes Operationalize models as web services with a single click; monetize in Azure Machine Learning Marketplace Flexible Built-in collection of best of breed algorithms with no coding required. Drop in custom R or use popular CRAN packages Integrated Drag, drop, and connect interface. Data sources with just a drop down run across any data. Fully managed No software to install, no hardware to manage; all you need is an Azure subscription.
Azure Machine Learning Solution Azure ML Studio  Browser-based  Designed for people without deep data science backgrounds  Supports deep science scenarios – R support, multiple models Azure Marketplace  Drag-and-deploy  Fast monetization of ML solutions and APIs  Quick source for free and third-party Azure ML APIs Azure cloud services  No software to install or infrastructure needed  Nearly unlimited file repositories via Azure Storage  Supports Azure data-related services – HDInsight, SQL Database Azure ML API  REST-based web service  Supports best-in-class algorithms  Reduces time from model experimentation to production
Azure ML Studio  Browser-based environment supporting general users and data scientists  Immutable library of models including search, discover, and reuse  Wide range of features, machine learning algorithms, and modeling strategies  Ability to quickly deploy models as Azure web services to the ML API service New experiment flow Streamlined experiment page New visualization for data tables Azure ML Studio
Azure ML API  Web-service and REST-based for easy creation and fast deployment  Allows general users and data scientists to run models as web services in minutes  Build apps that are easily accessible as web services, app plug-ins, or even mobile apps  Supports advanced data science, including R coding and 350 R packages included Custom data ingress and egress Extends ML Studio with customization Rich functionality – rules engine, R support, optimizer, simulation
AZURE MACHINE LEARNING STUDIO • https://studio.azureml.net • Online IDE to build, test, and deploy machine learning models • Drag and drop “modules”
Introduction to Machine learning and Deep Learning
Introduction to Machine learning and Deep Learning
Azure ML Data Preprocessing
GOAL OF MACHINE LEARNING “The goal of machine learning is to program computers to use example data or past experience to solve a given problem
CORTANA ANALYTICS SUITE successful experience with Azure ML https://www.youtube.com/watch?v=YxmAEMmwXYU
Introduction to Machine learning and Deep Learning
Introduction to Machine learning and Deep Learning
SQL SERVER ANALYSIS SERVICE
SSAS Vs Azure ML Features Usability Cost Support • End to end Product • Canned algorithm • Not possible to change algorithm • DMX Code •More Visual • Excel Version •It’s not easy to start •All users can use If you purchase SQL Sever: Free Few books and small online community • Current and up to date algorithm • Integration with R and Python • Cloud base • REST format • Hard to interpret • Drag and Drop UI • Customize the Algorithm Free version, limited options More online Community
OTHER RESOURCES

More Related Content

Introduction to Machine learning and Deep Learning

  • 2. NISHAN ARYAL Cloud App Developer CTO – Innovation Lab “Let’s learn together and share together” is what I believe www.aryalnishan.com.np
  • 3. If you invent a breakthrough in artificial intelligence, so machines can learn, that is worth 10 Microsoft
  • 4. What is Machine Learning?
  • 8. What is Machine Learning? • Using Computer Power to gain insight into data that might other be elusive • Credit Card Fraud Detection • Online Shopping recommendations • Self driving Cars and Tesla Motors • Tuning data into Solutions • Machine Learning Strategies • Supervised Learning • Unsupervised Learning
  • 11. Prepare Data • Import data • Pre-process data Train Model • Select Learning Algorithm and Build Model • Experiment/Iterate/Evaluate Make Operational • Prepare Model for Deployment • Deploy and call fro Applications
  • 12. You have been using ML since long
  • 14. Bing maps ships with ML Traffic Prediction Service Microsoft Kinect can watch users gestures Computers work on users behalf, filtering junk email Successful real-time speech-to-speech translation Microsoft Search Engine build with Machine Learning Enables data mining of databases MICROSOFT MACHINE LEARNING HISTORY
  • 15. SQL Server Data Mining Spam filtration Gestures understanding in Microsoft Kinect Azure Machine Learning Using Data Mining in search engines Bing Maps started to use ML for traffic estimate Voice recognition Microsoft & Machine Learning 1999 201220082004 201420102005
  • 19. Microsoft Azure Machine Learning  Reduced Complexity  Access Through Web Browser, no need to install any thing  Collaborate work with anyone  Visual composition, easy to use, No Coding  Good storage of Algorithm (Use in Bing search, Xbox..)  Have good support for R studio, Python and Jupyter notebook
  • 21. Azure ML Services pre-configured environment for deep learning using GPU instances Deploy in minutes Operationalize models as web services with a single click; monetize in Azure Machine Learning Marketplace Flexible Built-in collection of best of breed algorithms with no coding required. Drop in custom R or use popular CRAN packages Integrated Drag, drop, and connect interface. Data sources with just a drop down run across any data. Fully managed No software to install, no hardware to manage; all you need is an Azure subscription.
  • 22. Azure Machine Learning Solution Azure ML Studio  Browser-based  Designed for people without deep data science backgrounds  Supports deep science scenarios – R support, multiple models Azure Marketplace  Drag-and-deploy  Fast monetization of ML solutions and APIs  Quick source for free and third-party Azure ML APIs Azure cloud services  No software to install or infrastructure needed  Nearly unlimited file repositories via Azure Storage  Supports Azure data-related services – HDInsight, SQL Database Azure ML API  REST-based web service  Supports best-in-class algorithms  Reduces time from model experimentation to production
  • 23. Azure ML Studio  Browser-based environment supporting general users and data scientists  Immutable library of models including search, discover, and reuse  Wide range of features, machine learning algorithms, and modeling strategies  Ability to quickly deploy models as Azure web services to the ML API service New experiment flow Streamlined experiment page New visualization for data tables Azure ML Studio
  • 24. Azure ML API  Web-service and REST-based for easy creation and fast deployment  Allows general users and data scientists to run models as web services in minutes  Build apps that are easily accessible as web services, app plug-ins, or even mobile apps  Supports advanced data science, including R coding and 350 R packages included Custom data ingress and egress Extends ML Studio with customization Rich functionality – rules engine, R support, optimizer, simulation
  • 25. AZURE MACHINE LEARNING STUDIO • https://studio.azureml.net • Online IDE to build, test, and deploy machine learning models • Drag and drop “modules”
  • 28. Azure ML Data Preprocessing
  • 29. GOAL OF MACHINE LEARNING “The goal of machine learning is to program computers to use example data or past experience to solve a given problem
  • 30. CORTANA ANALYTICS SUITE successful experience with Azure ML https://www.youtube.com/watch?v=YxmAEMmwXYU
  • 34. SSAS Vs Azure ML Features Usability Cost Support • End to end Product • Canned algorithm • Not possible to change algorithm • DMX Code •More Visual • Excel Version •It’s not easy to start •All users can use If you purchase SQL Sever: Free Few books and small online community • Current and up to date algorithm • Integration with R and Python • Cloud base • REST format • Hard to interpret • Drag and Drop UI • Customize the Algorithm Free version, limited options More online Community

Editor's Notes

  1. Back in the 90s when the post office was wrestling with this issue, we were also working on Machine Learning, starting in 1991 when Microsoft Research was formed. As early as 1999 they were using it to help create email filters by predicting which emails were junk, and which were relevant. And as John Platt mentions—it’s a key technology that Microsoft uses to develop its own software. In 2004. Machine learning was part of Microsoft’s search engine It is also used in Bing Maps as part of the traffic prediction service. And many people know about how it was a key technology to make Kinect a reality, letting computers track people’s gestures and sort through what’s relevant and what’s not. Like filtering out a dog in the background to see a player’s movements. And today, this technology that has been developed over decades is becoming available commercially as part of Azure It’s this depth of experience with machine learning, testing and refining over years, using it to develop pretty much all Microsoft products, that makes Microsoft’s solution so robust.
  2. What gives the Azure ML solution so much flexibility is largely the Azure ML API. This API allows customers to build powerful ML solutions, customize Azure ML Studio to their particular needs, and integrate Azure ML into other data analysis solutions and software. And just like Azure ML Studio, the Azure ML API is accessible by users who are not sophisticated when it comes to advanced data analytics, but it also supports the needs of those who are. By enabling the API as a REST-based web service, we have made using it to run and publish models very easy. But by including richer functionality, including a rules engine, R support with 350 included packages, an optimizer, and simulation tools, we have also given it depth enough to address even the most advanced scenarios.