close

Se connecter

Se connecter avec OpenID

Azure Machine Learning: From design to integration

IntégréTéléchargement
Azure Machine Learning:
From design to integration
Peter Myers
M355
peter.myers@bitwisesolutions.com.au
http://www.linkedin.com/in/peterjsmyers
Machine Learning
Subfield of computer science and statistics that deals with
the construction and study of systems that can learn from
data, rather than follow only explicitly programmed
instructions
-Wikipedia
I need to add two
numbers together…
f()
num1, num2
I need to predict
customer profitability…
f()
Age, Marital Status, Gender, Yearly Income,
Total Children, Education, Occupation,
Home Owner, Commute Distance
Define
Objective
Collect
Data
Manage
Integrate
Prepare
Data
Publish
Evaluate
Models
Train
Models
High
competition
Strategic change
Expensive
Isolated data
Lots of buzz words
New markets
Tool chaos
Complexity
DATA
SCIENTIST
Traditional
approach
• Guessing
• Rules of thumb
• Trial and error
Consequences
• Lost opportunities
• Expensive operative
mistakes
•
•
•
How it works
Azure Portal
Azure Ops team
ML Studio
Data professionals & Data scientists
ML API service
Software developers
[Azure ops team]
Define
Objective
Collect
Data
Manage
Integrate
Prepare
Data
Publish
Evaluate
Models
Train
Models
Define
Objective
I need to predict
customer profitability…
…to deliver targeted display
advertising on the company
eCommerce web site, to:
Collect
Data
[Data professional]
Prepare
Data
[Data professional]
Train
Models
Evaluate
Models
[Data professional]
Publish
[Data professional]
Manage
[Azure ops team]
Integrate
•
•
•
•
•
•
[Software developer]
•
•
Imagine what you could use
Machine Learning for…
Ad
targeting
Churn
analysis
Image
detection &
classification
Equipment
monitoring
Recommendations
Forecasting
Spam
filtering
Fraud
detection
Anomaly
detection
One solution for machine learning
Web Apps
Mobile Apps
Power BI/Dashboards
ML API service
Application Developer
Azure Portal &
ML API service
ML Studio
HDInsight
Azure Storage
Azure Ops Team
Data Professional
Desktop Data
One solution for machine learning
Web Apps
Mobile Apps
Power BI/Dashboards
ML
service
and the Application Developer
MLAPIAPI
service
Business users easily access results
from anywhere, on any device
Developer
• Tested models available as a URL that can be called from any endpoint
Azure Portal
& ML API
service
Azure
Portal
&
and the Azure Ops Team
ML
APIMLservice
• Create
Studio workspace
• Assign storage account(s)
• Monitor ML consumption
• See alerts when model is ready
Azure
Opsmodels
Team
• Deploy
to web service
ML
MLStudio
Studio
HDInsight
and the Data Professional
•
•
•
•
Access and prepare data
Create, test and train models
Collaborate
One click to stage for
Data
Scientist
production
via the API service
Azure Storage
Desktop Data
Quick and easy extensibility with cloud functions such as
Power BI, Hadoop (Azure HDInsight) and cloud storage
http://azure.microsoft.com/en-us/services/machine-learning
http://azure.microsoft.com/en-us/documentation/services/machine-learning
http://azure.microsoft.com/en-us/documentation/articles/machine-learning-faq
http://azure.microsoft.com/en-us/pricing/details/machine-learning/
https://gallery.azureml.net
http://blogs.technet.com/b/machinelearning
http://www.revolutionanalytics.com
http://en.wikipedia.org/wiki/Paul_the_Octopus
Free Online Learning
http://aka.ms/mva
Subscribe to our fortnightly newsletter
http://aka.ms/technetnz
http://aka.ms/msdnnz
Sessions on Demand
http://aka.ms/ch9nz
© 2015 Microsoft Corporation. All rights reserved.
Microsoft, Windows and other product names are or may be registered trademarks and/or trademarks in the U.S. and/or other countries.
MICROSOFT MAKES NO WARRANTIES, EXPRESS, IMPLIED OR STATUTORY, AS TO THE INFORMATION IN THIS PRESENTATION.
Auteur
Документ
Catégorie
Без категории
Affichages
4
Taille du fichier
2 033 Кб
Étiquettes
1/--Pages
signaler