SlideShare a Scribd company logo
Bdug   introduction to azure machine learning
WHO AM I?
■ SolutionsArchitect at PwC Belgium
■ Office Development MVP - 4Years.
■ 18 years of experience as developer
■ Azure Certified SolutionsArchitect
■ Founder: Brussels Developers User
Group
■ Twitter: @levalencia
■ Blog: www.luisevalencia.com
Social networks
#brusselsdevug
@brusselsdevug
/brusselsdevug
linkedin.com/groups/13826566/
meetup.com/BrusselsDevelopersUserGroup
Hype
4
HandWringing*
• Bad
• Creepy
• Will kill Everyone
• Will take all our jobs
• Dangerous
• Should be banned
Terminator, Skynet, Somebody think of the children!
*The excessive display of concern or distress.
5
6
I don't have a problem with anyone who's critical
or sceptical about this stuff. I want you to be
critical and sceptical; that's fine, and there are
ethical concerns
7
8
Machine learning is not a new way to solve familiar
problems
9
Machine learning is a new way to solve new kind
of problems
10
11
That's a little cryptic, and when I say new kinds of problems, I don't mean
problems you have to invent or things you didn't even realize were
problems, or entirely new categories in the problem space. No, more often
these are situations that you're already perfectly aware of.You might not
even call them problems.You might think of them as business decisions or
issues or tasks, but where in the past you might've assumed that computers
just couldn't help you or couldn't help you that much. Like what?
How much is a good price
for this new product?
How often should we
send marketing emails?
Are there indications our
website is about to be
attacked?
Is the discussion positive
or negative?
12
But,What
really is
Machine
Learning then?
We take existing data,
Analyse it to identify patterns,
Then use the results
To make better predictions
About new data
14
15
16
17
18
19
20
21
22
23
Positive Samples Negative Samples
Classification
24
Incoming email - Classify as spam or not spam.
Website activity - Classify it as high value customer or not.
Incoming attachment - Classify it as a contract or not a contract
Classification Samples
25
What is AI?
27
AZURE MACHINE
LEARNING SERVICE
Bdug   introduction to azure machine learning
Workspaces
A workspace defines the boundary for a set of related machine learning assets.You can use
workspaces to group machine learning assets based on projects, deployment environments (for
example, test and production), teams, or some other organizing principle.The assets in a
workspace include:
■ Compute targets for development, training, and deployment.
■ Data for experimentation and model training.
■ Notebooks containing shared code and documentation.
■ Experiments, including run history with logged metrics and outputs.
■ Pipelines that define orchestrated multi-step processes.
■ Models that you have trained: A model is the result of a Azure Machine learning training Run
or some other model training process outside of Azure
Workspaces
The Azure resources created alongside
a workspace include:
■ A storage account - used to store files used by the workspace as well as data for
experiments and model training.
■ An Application Insights instance, used to monitor predictive services in the workspace.
■ An Azure KeyVault instance, used to manage secrets such as authentication keys and
credentials used by the workspace.
■ Virtual Machines, and their associated virtual hardware resources, used to provide
compute for notebook development in the workspace.
■ A container registry, used to manage containers for deployed models
Demos!
– Create Machine LearningWorkspace
– Compute
■ Jupyter
■ JupyterLab
■ RStudio
– Notebooks
■ Jupyter
■ JupyterLab
■ Inline
– Datasets
– Using a Dataset from Python
– Datastores
– Models
– Endpoints
■ Just a 3% improvement in detecting gift card fraud resulted in $40 million loss
avoidance
■ Does not have to be perfect to be valuable
■ Microsoft’sVision for ML
Make machine learning accessible to every enterprise, data scientist, developer,
information worker, consumer, and device anywhere in the world
Value of ML
■ Credit scoring first used by mail order business in 1950’s
■ 3 Fundamental Benefits
– Speed – evaluate millions of customers in seconds
– Accuracy - more accurate than humans – about 20-30%
– Consistency – a model will always generate same prediction given same set
of data – even a competent human expert will not depending on time of day,
mood or whether hungry or not – lots of evidence of this consistency problem
Really Focused on Predictive Analytics
■ Identifying people who don’t pay their taxes
■ Calculating probability of having a stroke in next 10 years
■ Spotting which credit card transactions are fraudulent
■ Selecting suspects in criminal cases
■ Deciding which candidate to offer a job to
■ Predicting how likely it is that a customer will become bankrupt
■ Predicting which customers are likely to defect to rival phone plan when their contract
reaches its end
■ Determining what books, music and films you are likely to purchase next
■ Forecasting life expectancy
Some Uses of Predictive Analytics
■ https://docs.microsoft.com/en-us/learn
Where to learn more
Thank you
https://www.luisevalencia.com
Twitter: @levalencia
Social networks
#brusselsdevug
@brusselsdevug
/brusselsdevug
linkedin.com/groups/13826566/
meetup.com/BrusselsDevelopersUserGroup

More Related Content

PDF
Startup Bootcamp 2013 — Michael Grinich
PDF
Practical model management in the age of Data science and ML
PPTX
AI-900 - Fundamental Principles of ML.pptx
PDF
The Machine Learning Audit
PDF
Adopting Data Science and Machine Learning in the financial enterprise
PDF
Ai in finance
PPTX
Business intelligence prof nikhat fatma mumtaz husain shaikh
PDF
Machine Learning Risk Management
Startup Bootcamp 2013 — Michael Grinich
Practical model management in the age of Data science and ML
AI-900 - Fundamental Principles of ML.pptx
The Machine Learning Audit
Adopting Data Science and Machine Learning in the financial enterprise
Ai in finance
Business intelligence prof nikhat fatma mumtaz husain shaikh
Machine Learning Risk Management

Similar to Bdug introduction to azure machine learning (20)

PPTX
1-210217184339.pptx
PDF
Digital analytics lecture1
PDF
So Now You’re a UiPath Developer – What’s Next?” What Role do You Play as Dev...
PPTX
AI Orange Belt - Session 4
PDF
Machine Learning and AI in Risk Management
PDF
Investing in ai driven startups
PPTX
machine learning introduction notes foRr
PDF
Machine Learning for Finance Master Class
PPTX
BA Overview.pptx
PDF
Preparing your Big Data start-up pitch
PDF
Applied AI Tech Talk: How to Setup a Data Science Dept
PDF
Data-X-Sparse-v2
PPTX
BAMarathon_DanielFylstra_Feb25.pptx
PPTX
Future se oct15
PDF
Big data and other buzzwords
PDF
No, you don't need to learn python
PDF
CFA-NY Workshop - Final slides
PDF
Data science guide
PPTX
Navigating-the-Challenges-and-Opportunites-of-AI-(NTFW).pptx
PDF
Doing Analytics Right - Designing and Automating Analytics
1-210217184339.pptx
Digital analytics lecture1
So Now You’re a UiPath Developer – What’s Next?” What Role do You Play as Dev...
AI Orange Belt - Session 4
Machine Learning and AI in Risk Management
Investing in ai driven startups
machine learning introduction notes foRr
Machine Learning for Finance Master Class
BA Overview.pptx
Preparing your Big Data start-up pitch
Applied AI Tech Talk: How to Setup a Data Science Dept
Data-X-Sparse-v2
BAMarathon_DanielFylstra_Feb25.pptx
Future se oct15
Big data and other buzzwords
No, you don't need to learn python
CFA-NY Workshop - Final slides
Data science guide
Navigating-the-Challenges-and-Opportunites-of-AI-(NTFW).pptx
Doing Analytics Right - Designing and Automating Analytics
Ad

More from Luis Valencia (14)

PPTX
Introduccion a azure cognitive search. e integracion con sharepoint office 36...
PPTX
Typescript design patterns applied to sharepoint framework - Sharepoint Satur...
PPTX
Sharepoint framework nivel avanzado
PPTX
Microsoft Graph Meetup Medellin
PPTX
Introducción a IoT Con NodeJS y IoT Hub
PPTX
Global Azure Bootcamp: Azure service fabric
PPTX
Sharepoint framework nivel avanzado
PPTX
Luis valencia introduction to share point webhooks
PPTX
Micro services architecture and service fabric
PPTX
Sharepoint Search 2013 Back to Front
PPTX
Introduccion a sharepoint framework
PPTX
Getting started with Office 365 APIs
PPTX
Moving full trust code to the cloud using repeatable patterns and best practices
PPTX
Charla desarrollo de apps con sharepoint y office 365
Introduccion a azure cognitive search. e integracion con sharepoint office 36...
Typescript design patterns applied to sharepoint framework - Sharepoint Satur...
Sharepoint framework nivel avanzado
Microsoft Graph Meetup Medellin
Introducción a IoT Con NodeJS y IoT Hub
Global Azure Bootcamp: Azure service fabric
Sharepoint framework nivel avanzado
Luis valencia introduction to share point webhooks
Micro services architecture and service fabric
Sharepoint Search 2013 Back to Front
Introduccion a sharepoint framework
Getting started with Office 365 APIs
Moving full trust code to the cloud using repeatable patterns and best practices
Charla desarrollo de apps con sharepoint y office 365
Ad

Recently uploaded (20)

PDF
NewMind AI Monthly Chronicles - July 2025
PDF
Chapter 3 Spatial Domain Image Processing.pdf
PDF
Architecting across the Boundaries of two Complex Domains - Healthcare & Tech...
PDF
cuic standard and advanced reporting.pdf
PPTX
VMware vSphere Foundation How to Sell Presentation-Ver1.4-2-14-2024.pptx
PDF
How UI/UX Design Impacts User Retention in Mobile Apps.pdf
PDF
Building Integrated photovoltaic BIPV_UPV.pdf
PDF
CIFDAQ's Market Insight: SEC Turns Pro Crypto
PPTX
Cloud computing and distributed systems.
PDF
Peak of Data & AI Encore- AI for Metadata and Smarter Workflows
PDF
Network Security Unit 5.pdf for BCA BBA.
PDF
NewMind AI Weekly Chronicles - August'25 Week I
PPTX
Big Data Technologies - Introduction.pptx
PDF
7 ChatGPT Prompts to Help You Define Your Ideal Customer Profile.pdf
PDF
Empathic Computing: Creating Shared Understanding
PDF
Approach and Philosophy of On baking technology
PPT
Teaching material agriculture food technology
PPTX
MYSQL Presentation for SQL database connectivity
PDF
Electronic commerce courselecture one. Pdf
PDF
Blue Purple Modern Animated Computer Science Presentation.pdf.pdf
NewMind AI Monthly Chronicles - July 2025
Chapter 3 Spatial Domain Image Processing.pdf
Architecting across the Boundaries of two Complex Domains - Healthcare & Tech...
cuic standard and advanced reporting.pdf
VMware vSphere Foundation How to Sell Presentation-Ver1.4-2-14-2024.pptx
How UI/UX Design Impacts User Retention in Mobile Apps.pdf
Building Integrated photovoltaic BIPV_UPV.pdf
CIFDAQ's Market Insight: SEC Turns Pro Crypto
Cloud computing and distributed systems.
Peak of Data & AI Encore- AI for Metadata and Smarter Workflows
Network Security Unit 5.pdf for BCA BBA.
NewMind AI Weekly Chronicles - August'25 Week I
Big Data Technologies - Introduction.pptx
7 ChatGPT Prompts to Help You Define Your Ideal Customer Profile.pdf
Empathic Computing: Creating Shared Understanding
Approach and Philosophy of On baking technology
Teaching material agriculture food technology
MYSQL Presentation for SQL database connectivity
Electronic commerce courselecture one. Pdf
Blue Purple Modern Animated Computer Science Presentation.pdf.pdf

Bdug introduction to azure machine learning

  • 2. WHO AM I? ■ SolutionsArchitect at PwC Belgium ■ Office Development MVP - 4Years. ■ 18 years of experience as developer ■ Azure Certified SolutionsArchitect ■ Founder: Brussels Developers User Group ■ Twitter: @levalencia ■ Blog: www.luisevalencia.com
  • 5. HandWringing* • Bad • Creepy • Will kill Everyone • Will take all our jobs • Dangerous • Should be banned Terminator, Skynet, Somebody think of the children! *The excessive display of concern or distress. 5
  • 6. 6 I don't have a problem with anyone who's critical or sceptical about this stuff. I want you to be critical and sceptical; that's fine, and there are ethical concerns
  • 7. 7
  • 8. 8 Machine learning is not a new way to solve familiar problems
  • 9. 9
  • 10. Machine learning is a new way to solve new kind of problems 10
  • 11. 11 That's a little cryptic, and when I say new kinds of problems, I don't mean problems you have to invent or things you didn't even realize were problems, or entirely new categories in the problem space. No, more often these are situations that you're already perfectly aware of.You might not even call them problems.You might think of them as business decisions or issues or tasks, but where in the past you might've assumed that computers just couldn't help you or couldn't help you that much. Like what?
  • 12. How much is a good price for this new product? How often should we send marketing emails? Are there indications our website is about to be attacked? Is the discussion positive or negative? 12
  • 14. We take existing data, Analyse it to identify patterns, Then use the results To make better predictions About new data 14
  • 15. 15
  • 16. 16
  • 17. 17
  • 18. 18
  • 19. 19
  • 20. 20
  • 21. 21
  • 22. 22
  • 23. 23
  • 24. Positive Samples Negative Samples Classification 24
  • 25. Incoming email - Classify as spam or not spam. Website activity - Classify it as high value customer or not. Incoming attachment - Classify it as a contract or not a contract Classification Samples 25
  • 27. 27
  • 30. Workspaces A workspace defines the boundary for a set of related machine learning assets.You can use workspaces to group machine learning assets based on projects, deployment environments (for example, test and production), teams, or some other organizing principle.The assets in a workspace include: ■ Compute targets for development, training, and deployment. ■ Data for experimentation and model training. ■ Notebooks containing shared code and documentation. ■ Experiments, including run history with logged metrics and outputs. ■ Pipelines that define orchestrated multi-step processes. ■ Models that you have trained: A model is the result of a Azure Machine learning training Run or some other model training process outside of Azure
  • 32. The Azure resources created alongside a workspace include: ■ A storage account - used to store files used by the workspace as well as data for experiments and model training. ■ An Application Insights instance, used to monitor predictive services in the workspace. ■ An Azure KeyVault instance, used to manage secrets such as authentication keys and credentials used by the workspace. ■ Virtual Machines, and their associated virtual hardware resources, used to provide compute for notebook development in the workspace. ■ A container registry, used to manage containers for deployed models
  • 33. Demos! – Create Machine LearningWorkspace – Compute ■ Jupyter ■ JupyterLab ■ RStudio – Notebooks ■ Jupyter ■ JupyterLab ■ Inline – Datasets – Using a Dataset from Python – Datastores – Models – Endpoints
  • 34. ■ Just a 3% improvement in detecting gift card fraud resulted in $40 million loss avoidance ■ Does not have to be perfect to be valuable ■ Microsoft’sVision for ML Make machine learning accessible to every enterprise, data scientist, developer, information worker, consumer, and device anywhere in the world Value of ML
  • 35. ■ Credit scoring first used by mail order business in 1950’s ■ 3 Fundamental Benefits – Speed – evaluate millions of customers in seconds – Accuracy - more accurate than humans – about 20-30% – Consistency – a model will always generate same prediction given same set of data – even a competent human expert will not depending on time of day, mood or whether hungry or not – lots of evidence of this consistency problem Really Focused on Predictive Analytics
  • 36. ■ Identifying people who don’t pay their taxes ■ Calculating probability of having a stroke in next 10 years ■ Spotting which credit card transactions are fraudulent ■ Selecting suspects in criminal cases ■ Deciding which candidate to offer a job to ■ Predicting how likely it is that a customer will become bankrupt ■ Predicting which customers are likely to defect to rival phone plan when their contract reaches its end ■ Determining what books, music and films you are likely to purchase next ■ Forecasting life expectancy Some Uses of Predictive Analytics