MACHINE LEARNING & AZURE
ML STUDIO
AMOL GHOLAP – PRINCIPAL CONSULTANT
AGHOLAP@GMAIL.COM
TWITTER - @AMOLGHOLAP
AGENDA
• Machine learning around us
• An Introduction to Machine Learning
• Traditional Programming Vs Machine Learning
• Microsoft AzureML Studio
• ML Demo using AzureML Studio
MACHINE LEARNING AROUND US
MACHINE LEARNING OVERVIEW
• Simplest definition: “The goal of machine learning is to program
computers to use example data or past experience to solve a
given problem.” – Introduction to Machine Learning, 2nd Edition, MIT Press
• ML often involves two primary techniques:
• Supervised Learning: Finding the mapping between inputs and
outputs using correct values to “train” a model
• Unsupervised Learning: Finding patterns in the input data (similar to
Density Estimates in Statistics)
TRADITIONAL PROGRAMMING VS MACHINE LEARNING
Traditional Programming
Machine Learning
Output
Data
Program
Ouput
Program / Algorithm
Data
Program Can predict output
CLASSES OF LEARNING
• Classification
• Binary classification –yes/no, 1/0, male/female
• Multi-class classification –{A, B, C, D}, {1, 2}, {teacher, student}
• Regression
• Predict a real value –temperature, stock value...
• Ranking
• Order items by some criteria –web search
• Clustering
• Partition items into group –twitter posts
STEPS TO BUILD A MACHINE LEARNING SOLUTION
AZURE ML
• Web only development studio
• Collaborate & work
• Industry Standard Algorithms available out of the box
• Support language “R” & “Python”
• Build, test, and deploy predictive analytics
AZURE MACHINE LEARNING WORKSPACE
BUSINESS PROBLEM TO BUSINESS VALUE
• HDInsight
• SQL Server VM
• SQL DB
• Blobs & tables
• Local Files
Publish API in minutes
Devices Applications
Dashboards
Data Microsoft Azure Machine Learning API
Storage
space
Web
Microsoft
Azure portal
Workspace
ML
Studio
Business problem Business valueModeling Deployment
• Desktop files
• Excel spreadsheet
• Other data
files on PC
Cloud
Local
DEMO
Q & A
RESOURCES
• http://blogs.technet.com/b/machinelearning/
• http://azure.microsoft.com/en-us/documentation/services/machine-learning/
• https://studio.azureml.net
• https://www.microsoftvirtualacademy.com/en-us/training-courses/getting-started-with-microsoft-azure-
machine-learning-8425
• http://azure.microsoft.com/en-us/documentation/videos/azure-machine-learning-for-software-engineers/
• https://channel9.msdn.com/events/TechEd/Europe/2014/DBI-B218
• https://archive.ics.uci.edu/ml/datasets.html
• https://azure.microsoft.com/en-us/documentation/articles/machine-learning-algorithm-cheat-sheet/
Thank you!!

Microsoft azure machine learning

  • 1.
    MACHINE LEARNING &AZURE ML STUDIO AMOL GHOLAP – PRINCIPAL CONSULTANT AGHOLAP@GMAIL.COM TWITTER - @AMOLGHOLAP
  • 2.
    AGENDA • Machine learningaround us • An Introduction to Machine Learning • Traditional Programming Vs Machine Learning • Microsoft AzureML Studio • ML Demo using AzureML Studio
  • 3.
  • 4.
    MACHINE LEARNING OVERVIEW •Simplest definition: “The goal of machine learning is to program computers to use example data or past experience to solve a given problem.” – Introduction to Machine Learning, 2nd Edition, MIT Press • ML often involves two primary techniques: • Supervised Learning: Finding the mapping between inputs and outputs using correct values to “train” a model • Unsupervised Learning: Finding patterns in the input data (similar to Density Estimates in Statistics)
  • 5.
    TRADITIONAL PROGRAMMING VSMACHINE LEARNING Traditional Programming Machine Learning Output Data Program Ouput Program / Algorithm Data Program Can predict output
  • 6.
    CLASSES OF LEARNING •Classification • Binary classification –yes/no, 1/0, male/female • Multi-class classification –{A, B, C, D}, {1, 2}, {teacher, student} • Regression • Predict a real value –temperature, stock value... • Ranking • Order items by some criteria –web search • Clustering • Partition items into group –twitter posts
  • 7.
    STEPS TO BUILDA MACHINE LEARNING SOLUTION
  • 8.
    AZURE ML • Webonly development studio • Collaborate & work • Industry Standard Algorithms available out of the box • Support language “R” & “Python” • Build, test, and deploy predictive analytics
  • 9.
  • 10.
    BUSINESS PROBLEM TOBUSINESS VALUE • HDInsight • SQL Server VM • SQL DB • Blobs & tables • Local Files Publish API in minutes Devices Applications Dashboards Data Microsoft Azure Machine Learning API Storage space Web Microsoft Azure portal Workspace ML Studio Business problem Business valueModeling Deployment • Desktop files • Excel spreadsheet • Other data files on PC Cloud Local
  • 12.
  • 13.
  • 14.
    RESOURCES • http://blogs.technet.com/b/machinelearning/ • http://azure.microsoft.com/en-us/documentation/services/machine-learning/ •https://studio.azureml.net • https://www.microsoftvirtualacademy.com/en-us/training-courses/getting-started-with-microsoft-azure- machine-learning-8425 • http://azure.microsoft.com/en-us/documentation/videos/azure-machine-learning-for-software-engineers/ • https://channel9.msdn.com/events/TechEd/Europe/2014/DBI-B218 • https://archive.ics.uci.edu/ml/datasets.html • https://azure.microsoft.com/en-us/documentation/articles/machine-learning-algorithm-cheat-sheet/
  • 15.