SlideShare a Scribd company logo
#DeltatreInnovationLab
Clemente Giorio
R&D Senior Software Engineer
Gianni Rosa Gallina
R&D Senior Software Engineer
Deltatre powers
the world’s top
fan engagement
experiences
Global team of 1,000+ experts delivering
technology and user experiences across
19 offices
Over 30 years of business with
hundreds of awards
EMEA
Turin
London
Geneva
Hamburg
Munich
Paris
Prague
Brno
Skopje
AMERICAS
Los Angeles
New York
Utah
APAC
Mumbai
Singapore
Tokyo
Sydney
Hong Kong
A B O U T D E L T A T R E
3
DESKTOP CLOUDWEB MOBILE ML
.NET
Your platform for building anything
IoTGAMING
“It has exquisite buttons …
with long sleeves …works for
casual as well as business
settings”{f(x) {f(x)
Machine Learning
“Programming the UnProgrammable”
f(x)
Model
Machine Learning creates a
using this data
Machine Learning
“Programming the UnProgrammable”
ML.NET 1.0
Machine Learning framework for building custom ML Models
Custom ML made easy
Automated ML and Tools (Model Builder and CLI)
Proven at scale
Azure, Office, Windows
Extensible
TensorFlow, ONNX and Infer.NET
Cross-platform and open-source
Runs everywhere
A few things you can do with ML.NET
ML.NET tutorials GitHub samples
Building blocks for a Data Science Project
Data
sources
1. Data
Example
Comment Text Sentiment
Wow... Loved this place. 1
Crust is not good. 0
Not tasty and the texture was just nasty. 0
The selection on the menu was great. 1
Text Featurizer
Featurized Text
[0.76, 0.65, 0.44, …]
[0.98, 0.43, 0.54, …]
[0.35, 0.73, 0.46, …]
[0.39, 0, 0.75, …]
Example
Text
Wow... Loved this place.
Crust is not good.
Not tasty and the texture was just nasty.
The selection on the menu was great.
2. Transformers
Example
Estimator
Comment Sentiment
Wow... Loved this place. 1
Crust is not good. 0
Not tasty and the texture was just nasty. 0
The selection on the menu was great. 0
3. Estimators
Comment Text Sentiment
Wow... Loved this place. 1
Crust is not good. 0
Not tasty and the texture was just nasty. 0
The selection on the menu was great. 1
Yelp review dataset
Features (input) Label (output)
Sentiment Analysis
Is this a positive comment? Yes or no
Building blocks for a Data Science Project
Data
sources
What is automated
machine learning?
Automated machine learning (automated ML)
automates feature engineering, algorithm and
hyperparameter selection to find the best model
for your data.
Automated ML Mission
Democratize AI Scale AIAccelerate AI
Enable automated building of machine learning with the goal of accelerating, democratizing and scaling AI
Enable Domain Experts & Developers to
get rapidly build AI solutions
Improve Productivity for Data Scientists,
Citizen Data Scientists, App Developers &
Analysts
Build AI solutions at scale in an automated
fashion
Machine Learning for Everyone
Automated
Machine
Learning
Data
Scientist
Citizen
Data
Scientist
Data
Analyst
Data
Engineer
Developer
How much is this car worth?
Machine Learning Problem Example
Mileage
Condition
Car brand
Year of make
Regulations
…
Parameter 1
Parameter 2
Parameter 3
Parameter 4
…
Gradient Boosted
Nearest Neighbors
SVM
Bayesian Regression
LGBM
…
Mileage Gradient Boosted Criterion
Loss
Min Samples Split
Min Samples Leaf
Others Model
Which algorithm? Which parameters?Which features?
Car brand
Year of make
Criterion
Loss
Min Samples Split
Min Samples Leaf
Others
N Neighbors
Weights
Metric
P
Others
Which algorithm? Which parameters?Which features?
Mileage
Condition
Car brand
Year of make
Regulations
…
Gradient Boosted
Nearest Neighbors
SVM
Bayesian Regression
LGBM
…
Nearest Neighbors
Model
Iterate
Gradient BoostedMileage
Car brand
Year of make
Car brand
Year of make
Condition
Which algorithm? Which parameters?Which features?
Iterate
Enter data
Define goals
Apply constraints
OutputInput Intelligently test multiple models in parallel
Optimized model
Automated ML Capabilities
Data
Preprocessing
Feature
Engineering
Algorithm
Selection
Hyper-parameter
Tuning
Model
Recommendation
Interpretability
& Explaining
1. 2 3. 4. 5. 6.
Automated ML
Class imbalance
Train-Test split, CV, rolling CV
Missing value imputation
Detect high cardinality features
Detect leaky features
Detect overfitting
Model Interpretability / Feature Importance
ML.NET AutoML
Automated Machine Learning (AutoML)
On the command line, with the ML.NET CLI
mlnet auto-train --task binary-classification --dataset "yelp_labelled.txt" --label-column-index 1 --has-header
false --max-exploration-time 10
With a graphical user interface, with the the ML.NET Model Builder
https://github.com/marktab/machinelearning-
samples/tree/master/samples/csharp/getting-
started/BinaryClassification_AutoML
Via an application, with the automated ML API
What’s new?
ML.NET v1.4 (announced at Microsoft Ignite)
Image classification based on deep neural network retraining with GPU support
Support for Native DNN (Deep Neural Network) transfer learning with ML.NET
Improvements for Image Classification
• GPU support on Windows and Linux
• Predictions on in-memory images
• Training early stopping
• Learning rate scheduling (Exponential Decay, Polynomial Decay)
• Added additional supported DNN architectures to the Image Classifier
o Inception v3
o ResNet 101 v2
o ResNet 50 v2
o MobileNet v2
https://devblogs.microsoft.com/dotnet/announcing-ml-net-1-4-global-availability-machine-learning-for-net/
Updated Model Builder in Visual Studio
Use latest engine and includes new features (visual experience for local Image Classification model training)
ML.NET v1.4 (announced at Microsoft Ignite)
Database Loader
Load data from databases into the IDataView →model training directly
against relational databases
PredictionEnginePool for scalable deployments
Optimization when deploy an ML model into multithreaded and
scalable .NET Core web applications and services
https://devblogs.microsoft.com/dotnet/announcing-ml-net-1-4-global-availability-machine-learning-for-net/
Enhanced for .NET Core 3.0
Take advantage of the new features when running in a .NET Core 3.0 application
Use ML.NET in Jupyter notebooks
.NET Support in Jupyter notebooks
https://dotnet.microsoft.com/apps/data/spark
https://dotnet.microsoft.com/learn/dotnet/architecture-guides
About
NimbusML
• NimbusML provides state-of-the-art ML
algorithms, transforms and components, aiming
to make them useful for all developers, data
scientists, and information workers and helpful
in all products, services and devices.
• The components are authored by the team
members, as well as numerous contributors
from MSR, CISL, Bing and other teams at
Microsoft.
• nimbusml is interoperable with scikit-learn
estimators and transforms, while adding a suite
of highly optimized algorithms written in C++
and C# for speed and performance.
NimbusML
Features
NimbusML trainers and transforms support
the following data structures for the fit() and
transform() methods:
• numpy.ndarray
• scipy.sparse_cst
• pandas.DataFrame.
NimbusML also supports streaming from files
without loading the dataset into memory,
which allows training on data significantly
exceeding memory using FileDataStream.
• With FileDataStream, NimbusML is able to handle up to
billion features and billions of training examples for
select algorithms
http://dot.net/ml
http://aka.ms/ai-mlnetsamples
http://aka.ms/mlnetdocs
http://aka.ms/mlnet
Thank You!
Questions?
Clemente Giorio
R&D Senior Software Engineer @ Deltatre
▪ Augmented/Mixed/Virtual Reality
▪ Artificial Intelligence, Machine Learning
▪ Internet of Things
▪ Embedded Apps
▪ Multimodal Tracking
@tinux80
Author
About us
About us
Ing. Gianni ROSA GALLINA
R&D Senior Software Engineer @ Deltatre
▪ AI, Machine Learning, Deep Learning on multimedia content
▪ Virtual/Augmented/Mixed Reality
▪ Immersive video streaming & 3D graphics for sport events
▪ Cloud solutions, web backends, serverless, video workflows
▪ Mobile apps dev (Windows / Android / Xamarin)
▪ End-to-end solutions with Microsoft Azure
@giannirg
http://gianni.rosagallina.com
Author
Introduction to ML.NET

More Related Content

What's hot

MLSEV Virtual. From my First BigML Project to Production
MLSEV Virtual. From my First BigML Project to ProductionMLSEV Virtual. From my First BigML Project to Production
MLSEV Virtual. From my First BigML Project to Production
BigML, Inc
 
Apache Liminal (Incubating)—Orchestrate the Machine Learning Pipeline
Apache Liminal (Incubating)—Orchestrate the Machine Learning PipelineApache Liminal (Incubating)—Orchestrate the Machine Learning Pipeline
Apache Liminal (Incubating)—Orchestrate the Machine Learning Pipeline
Databricks
 
Machine Learning for .NET Developers - ADC21
Machine Learning for .NET Developers - ADC21Machine Learning for .NET Developers - ADC21
Machine Learning for .NET Developers - ADC21
Gülden Bilgütay
 
2021 02 23 MVP Fusion Getting Started with Machine Learning.Net and AutoML
2021 02 23 MVP Fusion Getting Started with Machine Learning.Net and AutoML2021 02 23 MVP Fusion Getting Started with Machine Learning.Net and AutoML
2021 02 23 MVP Fusion Getting Started with Machine Learning.Net and AutoML
Bruno Capuano
 
Scale machine learning deployment
Scale machine learning deploymentScale machine learning deployment
Scale machine learning deployment
Gang Tao
 
“Houston, we have a model...” Introduction to MLOps
“Houston, we have a model...” Introduction to MLOps“Houston, we have a model...” Introduction to MLOps
“Houston, we have a model...” Introduction to MLOps
Rui Quintino
 
Getting Started with Azure AutoML
Getting Started with Azure AutoMLGetting Started with Azure AutoML
Getting Started with Azure AutoML
Vivek Raja P S
 
Introduction to ML.NET
Introduction to ML.NETIntroduction to ML.NET
Introduction to ML.NET
Marco Parenzan
 
Applied machine learning at facebook a datacenter infrastructure perspective...
Applied machine learning at facebook  a datacenter infrastructure perspective...Applied machine learning at facebook  a datacenter infrastructure perspective...
Applied machine learning at facebook a datacenter infrastructure perspective...
Shunya Ueta
 
Is that a Time Machine? Some Design Patterns for Real World Machine Learning ...
Is that a Time Machine? Some Design Patterns for Real World Machine Learning ...Is that a Time Machine? Some Design Patterns for Real World Machine Learning ...
Is that a Time Machine? Some Design Patterns for Real World Machine Learning ...
Justin Basilico
 
MLFlow: Platform for Complete Machine Learning Lifecycle
MLFlow: Platform for Complete Machine Learning Lifecycle MLFlow: Platform for Complete Machine Learning Lifecycle
MLFlow: Platform for Complete Machine Learning Lifecycle
Databricks
 
Ai use cases
Ai use casesAi use cases
Ai use cases
Sparsh Agarwal
 
Building A Machine Learning Platform At Quora (1)
Building A Machine Learning Platform At Quora (1)Building A Machine Learning Platform At Quora (1)
Building A Machine Learning Platform At Quora (1)Nikhil Garg
 
Machine Learning With ML.NET
Machine Learning With ML.NETMachine Learning With ML.NET
Machine Learning With ML.NET
Dev Raj Gautam
 
The A-Z of Data: Introduction to MLOps
The A-Z of Data: Introduction to MLOpsThe A-Z of Data: Introduction to MLOps
The A-Z of Data: Introduction to MLOps
DataPhoenix
 
Why is dev ops for machine learning so different - dataxdays
Why is dev ops for machine learning so different  - dataxdaysWhy is dev ops for machine learning so different  - dataxdays
Why is dev ops for machine learning so different - dataxdays
Ryan Dawson
 
What's Next for MLflow in 2019
What's Next for MLflow in 2019What's Next for MLflow in 2019
What's Next for MLflow in 2019
Anyscale
 
SAIS2018 - Fact Store At Netflix Scale
SAIS2018 - Fact Store At Netflix ScaleSAIS2018 - Fact Store At Netflix Scale
SAIS2018 - Fact Store At Netflix Scale
Nitin S
 
Managers guide to effective building of machine learning products
Managers guide to effective building of machine learning productsManagers guide to effective building of machine learning products
Managers guide to effective building of machine learning products
Gianmario Spacagna
 
Lessons Learned from Building Machine Learning Software at Netflix
Lessons Learned from Building Machine Learning Software at NetflixLessons Learned from Building Machine Learning Software at Netflix
Lessons Learned from Building Machine Learning Software at Netflix
Justin Basilico
 

What's hot (20)

MLSEV Virtual. From my First BigML Project to Production
MLSEV Virtual. From my First BigML Project to ProductionMLSEV Virtual. From my First BigML Project to Production
MLSEV Virtual. From my First BigML Project to Production
 
Apache Liminal (Incubating)—Orchestrate the Machine Learning Pipeline
Apache Liminal (Incubating)—Orchestrate the Machine Learning PipelineApache Liminal (Incubating)—Orchestrate the Machine Learning Pipeline
Apache Liminal (Incubating)—Orchestrate the Machine Learning Pipeline
 
Machine Learning for .NET Developers - ADC21
Machine Learning for .NET Developers - ADC21Machine Learning for .NET Developers - ADC21
Machine Learning for .NET Developers - ADC21
 
2021 02 23 MVP Fusion Getting Started with Machine Learning.Net and AutoML
2021 02 23 MVP Fusion Getting Started with Machine Learning.Net and AutoML2021 02 23 MVP Fusion Getting Started with Machine Learning.Net and AutoML
2021 02 23 MVP Fusion Getting Started with Machine Learning.Net and AutoML
 
Scale machine learning deployment
Scale machine learning deploymentScale machine learning deployment
Scale machine learning deployment
 
“Houston, we have a model...” Introduction to MLOps
“Houston, we have a model...” Introduction to MLOps“Houston, we have a model...” Introduction to MLOps
“Houston, we have a model...” Introduction to MLOps
 
Getting Started with Azure AutoML
Getting Started with Azure AutoMLGetting Started with Azure AutoML
Getting Started with Azure AutoML
 
Introduction to ML.NET
Introduction to ML.NETIntroduction to ML.NET
Introduction to ML.NET
 
Applied machine learning at facebook a datacenter infrastructure perspective...
Applied machine learning at facebook  a datacenter infrastructure perspective...Applied machine learning at facebook  a datacenter infrastructure perspective...
Applied machine learning at facebook a datacenter infrastructure perspective...
 
Is that a Time Machine? Some Design Patterns for Real World Machine Learning ...
Is that a Time Machine? Some Design Patterns for Real World Machine Learning ...Is that a Time Machine? Some Design Patterns for Real World Machine Learning ...
Is that a Time Machine? Some Design Patterns for Real World Machine Learning ...
 
MLFlow: Platform for Complete Machine Learning Lifecycle
MLFlow: Platform for Complete Machine Learning Lifecycle MLFlow: Platform for Complete Machine Learning Lifecycle
MLFlow: Platform for Complete Machine Learning Lifecycle
 
Ai use cases
Ai use casesAi use cases
Ai use cases
 
Building A Machine Learning Platform At Quora (1)
Building A Machine Learning Platform At Quora (1)Building A Machine Learning Platform At Quora (1)
Building A Machine Learning Platform At Quora (1)
 
Machine Learning With ML.NET
Machine Learning With ML.NETMachine Learning With ML.NET
Machine Learning With ML.NET
 
The A-Z of Data: Introduction to MLOps
The A-Z of Data: Introduction to MLOpsThe A-Z of Data: Introduction to MLOps
The A-Z of Data: Introduction to MLOps
 
Why is dev ops for machine learning so different - dataxdays
Why is dev ops for machine learning so different  - dataxdaysWhy is dev ops for machine learning so different  - dataxdays
Why is dev ops for machine learning so different - dataxdays
 
What's Next for MLflow in 2019
What's Next for MLflow in 2019What's Next for MLflow in 2019
What's Next for MLflow in 2019
 
SAIS2018 - Fact Store At Netflix Scale
SAIS2018 - Fact Store At Netflix ScaleSAIS2018 - Fact Store At Netflix Scale
SAIS2018 - Fact Store At Netflix Scale
 
Managers guide to effective building of machine learning products
Managers guide to effective building of machine learning productsManagers guide to effective building of machine learning products
Managers guide to effective building of machine learning products
 
Lessons Learned from Building Machine Learning Software at Netflix
Lessons Learned from Building Machine Learning Software at NetflixLessons Learned from Building Machine Learning Software at Netflix
Lessons Learned from Building Machine Learning Software at Netflix
 

Similar to Introduction to ML.NET

201909 Automated ML for Developers
201909 Automated ML for Developers201909 Automated ML for Developers
201909 Automated ML for Developers
Mark Tabladillo
 
2018 12 18 Tech Valley UserGroup Machine Learning.Net
2018 12 18 Tech Valley UserGroup Machine Learning.Net2018 12 18 Tech Valley UserGroup Machine Learning.Net
2018 12 18 Tech Valley UserGroup Machine Learning.Net
Bruno Capuano
 
Webinar GLUGNet - Machine Learning.Net and Windows Machine Learning
Webinar GLUGNet - Machine Learning.Net and Windows Machine LearningWebinar GLUGNet - Machine Learning.Net and Windows Machine Learning
Webinar GLUGNet - Machine Learning.Net and Windows Machine Learning
Bruno Capuano
 
Norman Sasono - Incorporating AI/ML into Your Application Architecture
Norman Sasono - Incorporating AI/ML into Your Application ArchitectureNorman Sasono - Incorporating AI/ML into Your Application Architecture
Norman Sasono - Incorporating AI/ML into Your Application Architecture
Agile Impact Conference
 
Norman Sasono - Incorporating AI/ML into Your Application Architecture
Norman Sasono - Incorporating AI/ML into Your Application ArchitectureNorman Sasono - Incorporating AI/ML into Your Application Architecture
Norman Sasono - Incorporating AI/ML into Your Application Architecture
Agile Impact
 
Machine Learning para devs com ML.NET
Machine Learning para devs com ML.NETMachine Learning para devs com ML.NET
Machine Learning para devs com ML.NET
Letticia Nicoli
 
Deep AutoViML For Tensorflow Models and MLOps Workflows
Deep AutoViML For Tensorflow Models and MLOps WorkflowsDeep AutoViML For Tensorflow Models and MLOps Workflows
Deep AutoViML For Tensorflow Models and MLOps Workflows
Bill Liu
 
Deep Learning with CNTK
Deep Learning with CNTKDeep Learning with CNTK
Deep Learning with CNTK
Ashish Jaiman
 
Azure Machine Learning 101
Azure Machine Learning 101Azure Machine Learning 101
Azure Machine Learning 101
Renato Jovic
 
Build, Train, and Deploy ML Models at Scale
Build, Train, and Deploy ML Models at ScaleBuild, Train, and Deploy ML Models at Scale
Build, Train, and Deploy ML Models at Scale
Amazon Web Services
 
2018 11 14 Artificial Intelligence and Machine Learning in Azure
2018 11 14 Artificial Intelligence and Machine Learning in Azure2018 11 14 Artificial Intelligence and Machine Learning in Azure
2018 11 14 Artificial Intelligence and Machine Learning in Azure
Bruno Capuano
 
Building an ML model with zero code
Building an ML model with zero codeBuilding an ML model with zero code
Building an ML model with zero code
Nick Trogh
 
Serverless machine learning architectures at Helixa
Serverless machine learning architectures at HelixaServerless machine learning architectures at Helixa
Serverless machine learning architectures at Helixa
Data Science Milan
 
Leverage the power of machine learning on windows
Leverage the power of machine learning on windowsLeverage the power of machine learning on windows
Leverage the power of machine learning on windows
Mia Chang
 
Building Machine Learning Models Automatically (June 2020)
Building Machine Learning Models Automatically (June 2020)Building Machine Learning Models Automatically (June 2020)
Building Machine Learning Models Automatically (June 2020)
Julien SIMON
 
201906 01 Introduction to ML.NET 1.0
201906 01 Introduction to ML.NET 1.0201906 01 Introduction to ML.NET 1.0
201906 01 Introduction to ML.NET 1.0
Mark Tabladillo
 
What are the Unique Challenges and Opportunities in Systems for ML?
What are the Unique Challenges and Opportunities in Systems for ML?What are the Unique Challenges and Opportunities in Systems for ML?
What are the Unique Challenges and Opportunities in Systems for ML?
Matei Zaharia
 
Machine Learning
Machine LearningMachine Learning
Machine Learning
Ramiro Aduviri Velasco
 
2021 06 19 ms student ambassadors nigeria ml net 01 slide-share
2021 06 19 ms student ambassadors nigeria ml net 01   slide-share2021 06 19 ms student ambassadors nigeria ml net 01   slide-share
2021 06 19 ms student ambassadors nigeria ml net 01 slide-share
Bruno Capuano
 
Build 2019 Recap
Build 2019 RecapBuild 2019 Recap
Build 2019 Recap
Eran Stiller
 

Similar to Introduction to ML.NET (20)

201909 Automated ML for Developers
201909 Automated ML for Developers201909 Automated ML for Developers
201909 Automated ML for Developers
 
2018 12 18 Tech Valley UserGroup Machine Learning.Net
2018 12 18 Tech Valley UserGroup Machine Learning.Net2018 12 18 Tech Valley UserGroup Machine Learning.Net
2018 12 18 Tech Valley UserGroup Machine Learning.Net
 
Webinar GLUGNet - Machine Learning.Net and Windows Machine Learning
Webinar GLUGNet - Machine Learning.Net and Windows Machine LearningWebinar GLUGNet - Machine Learning.Net and Windows Machine Learning
Webinar GLUGNet - Machine Learning.Net and Windows Machine Learning
 
Norman Sasono - Incorporating AI/ML into Your Application Architecture
Norman Sasono - Incorporating AI/ML into Your Application ArchitectureNorman Sasono - Incorporating AI/ML into Your Application Architecture
Norman Sasono - Incorporating AI/ML into Your Application Architecture
 
Norman Sasono - Incorporating AI/ML into Your Application Architecture
Norman Sasono - Incorporating AI/ML into Your Application ArchitectureNorman Sasono - Incorporating AI/ML into Your Application Architecture
Norman Sasono - Incorporating AI/ML into Your Application Architecture
 
Machine Learning para devs com ML.NET
Machine Learning para devs com ML.NETMachine Learning para devs com ML.NET
Machine Learning para devs com ML.NET
 
Deep AutoViML For Tensorflow Models and MLOps Workflows
Deep AutoViML For Tensorflow Models and MLOps WorkflowsDeep AutoViML For Tensorflow Models and MLOps Workflows
Deep AutoViML For Tensorflow Models and MLOps Workflows
 
Deep Learning with CNTK
Deep Learning with CNTKDeep Learning with CNTK
Deep Learning with CNTK
 
Azure Machine Learning 101
Azure Machine Learning 101Azure Machine Learning 101
Azure Machine Learning 101
 
Build, Train, and Deploy ML Models at Scale
Build, Train, and Deploy ML Models at ScaleBuild, Train, and Deploy ML Models at Scale
Build, Train, and Deploy ML Models at Scale
 
2018 11 14 Artificial Intelligence and Machine Learning in Azure
2018 11 14 Artificial Intelligence and Machine Learning in Azure2018 11 14 Artificial Intelligence and Machine Learning in Azure
2018 11 14 Artificial Intelligence and Machine Learning in Azure
 
Building an ML model with zero code
Building an ML model with zero codeBuilding an ML model with zero code
Building an ML model with zero code
 
Serverless machine learning architectures at Helixa
Serverless machine learning architectures at HelixaServerless machine learning architectures at Helixa
Serverless machine learning architectures at Helixa
 
Leverage the power of machine learning on windows
Leverage the power of machine learning on windowsLeverage the power of machine learning on windows
Leverage the power of machine learning on windows
 
Building Machine Learning Models Automatically (June 2020)
Building Machine Learning Models Automatically (June 2020)Building Machine Learning Models Automatically (June 2020)
Building Machine Learning Models Automatically (June 2020)
 
201906 01 Introduction to ML.NET 1.0
201906 01 Introduction to ML.NET 1.0201906 01 Introduction to ML.NET 1.0
201906 01 Introduction to ML.NET 1.0
 
What are the Unique Challenges and Opportunities in Systems for ML?
What are the Unique Challenges and Opportunities in Systems for ML?What are the Unique Challenges and Opportunities in Systems for ML?
What are the Unique Challenges and Opportunities in Systems for ML?
 
Machine Learning
Machine LearningMachine Learning
Machine Learning
 
2021 06 19 ms student ambassadors nigeria ml net 01 slide-share
2021 06 19 ms student ambassadors nigeria ml net 01   slide-share2021 06 19 ms student ambassadors nigeria ml net 01   slide-share
2021 06 19 ms student ambassadors nigeria ml net 01 slide-share
 
Build 2019 Recap
Build 2019 RecapBuild 2019 Recap
Build 2019 Recap
 

Recently uploaded

Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
Dorra BARTAGUIZ
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
DianaGray10
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
Paul Groth
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
Elena Simperl
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
Cheryl Hung
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
ControlCase
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
Safe Software
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
RTTS
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
g2nightmarescribd
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
Thijs Feryn
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
OnBoard
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
KatiaHIMEUR1
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
UiPathCommunity
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Albert Hoitingh
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Product School
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 

Recently uploaded (20)

Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 

Introduction to ML.NET

  • 1.
  • 2. #DeltatreInnovationLab Clemente Giorio R&D Senior Software Engineer Gianni Rosa Gallina R&D Senior Software Engineer
  • 3. Deltatre powers the world’s top fan engagement experiences Global team of 1,000+ experts delivering technology and user experiences across 19 offices Over 30 years of business with hundreds of awards EMEA Turin London Geneva Hamburg Munich Paris Prague Brno Skopje AMERICAS Los Angeles New York Utah APAC Mumbai Singapore Tokyo Sydney Hong Kong A B O U T D E L T A T R E 3
  • 4.
  • 5. DESKTOP CLOUDWEB MOBILE ML .NET Your platform for building anything IoTGAMING
  • 6. “It has exquisite buttons … with long sleeves …works for casual as well as business settings”{f(x) {f(x) Machine Learning “Programming the UnProgrammable”
  • 7. f(x) Model Machine Learning creates a using this data Machine Learning “Programming the UnProgrammable”
  • 8. ML.NET 1.0 Machine Learning framework for building custom ML Models Custom ML made easy Automated ML and Tools (Model Builder and CLI) Proven at scale Azure, Office, Windows Extensible TensorFlow, ONNX and Infer.NET Cross-platform and open-source Runs everywhere
  • 9. A few things you can do with ML.NET ML.NET tutorials GitHub samples
  • 10. Building blocks for a Data Science Project Data sources
  • 11. 1. Data Example Comment Text Sentiment Wow... Loved this place. 1 Crust is not good. 0 Not tasty and the texture was just nasty. 0 The selection on the menu was great. 1
  • 12. Text Featurizer Featurized Text [0.76, 0.65, 0.44, …] [0.98, 0.43, 0.54, …] [0.35, 0.73, 0.46, …] [0.39, 0, 0.75, …] Example Text Wow... Loved this place. Crust is not good. Not tasty and the texture was just nasty. The selection on the menu was great. 2. Transformers
  • 13. Example Estimator Comment Sentiment Wow... Loved this place. 1 Crust is not good. 0 Not tasty and the texture was just nasty. 0 The selection on the menu was great. 0 3. Estimators
  • 14. Comment Text Sentiment Wow... Loved this place. 1 Crust is not good. 0 Not tasty and the texture was just nasty. 0 The selection on the menu was great. 1 Yelp review dataset Features (input) Label (output) Sentiment Analysis Is this a positive comment? Yes or no
  • 15.
  • 16.
  • 17. Building blocks for a Data Science Project Data sources
  • 18. What is automated machine learning? Automated machine learning (automated ML) automates feature engineering, algorithm and hyperparameter selection to find the best model for your data.
  • 19. Automated ML Mission Democratize AI Scale AIAccelerate AI Enable automated building of machine learning with the goal of accelerating, democratizing and scaling AI Enable Domain Experts & Developers to get rapidly build AI solutions Improve Productivity for Data Scientists, Citizen Data Scientists, App Developers & Analysts Build AI solutions at scale in an automated fashion
  • 20. Machine Learning for Everyone Automated Machine Learning Data Scientist Citizen Data Scientist Data Analyst Data Engineer Developer
  • 21. How much is this car worth? Machine Learning Problem Example
  • 22. Mileage Condition Car brand Year of make Regulations … Parameter 1 Parameter 2 Parameter 3 Parameter 4 … Gradient Boosted Nearest Neighbors SVM Bayesian Regression LGBM … Mileage Gradient Boosted Criterion Loss Min Samples Split Min Samples Leaf Others Model Which algorithm? Which parameters?Which features? Car brand Year of make
  • 23. Criterion Loss Min Samples Split Min Samples Leaf Others N Neighbors Weights Metric P Others Which algorithm? Which parameters?Which features? Mileage Condition Car brand Year of make Regulations … Gradient Boosted Nearest Neighbors SVM Bayesian Regression LGBM … Nearest Neighbors Model Iterate Gradient BoostedMileage Car brand Year of make Car brand Year of make Condition
  • 24. Which algorithm? Which parameters?Which features? Iterate
  • 25. Enter data Define goals Apply constraints OutputInput Intelligently test multiple models in parallel Optimized model
  • 28. Class imbalance Train-Test split, CV, rolling CV Missing value imputation Detect high cardinality features Detect leaky features Detect overfitting Model Interpretability / Feature Importance
  • 31. On the command line, with the ML.NET CLI mlnet auto-train --task binary-classification --dataset "yelp_labelled.txt" --label-column-index 1 --has-header false --max-exploration-time 10
  • 32. With a graphical user interface, with the the ML.NET Model Builder
  • 34.
  • 36. ML.NET v1.4 (announced at Microsoft Ignite) Image classification based on deep neural network retraining with GPU support Support for Native DNN (Deep Neural Network) transfer learning with ML.NET Improvements for Image Classification • GPU support on Windows and Linux • Predictions on in-memory images • Training early stopping • Learning rate scheduling (Exponential Decay, Polynomial Decay) • Added additional supported DNN architectures to the Image Classifier o Inception v3 o ResNet 101 v2 o ResNet 50 v2 o MobileNet v2 https://devblogs.microsoft.com/dotnet/announcing-ml-net-1-4-global-availability-machine-learning-for-net/ Updated Model Builder in Visual Studio Use latest engine and includes new features (visual experience for local Image Classification model training)
  • 37. ML.NET v1.4 (announced at Microsoft Ignite) Database Loader Load data from databases into the IDataView →model training directly against relational databases PredictionEnginePool for scalable deployments Optimization when deploy an ML model into multithreaded and scalable .NET Core web applications and services https://devblogs.microsoft.com/dotnet/announcing-ml-net-1-4-global-availability-machine-learning-for-net/ Enhanced for .NET Core 3.0 Take advantage of the new features when running in a .NET Core 3.0 application Use ML.NET in Jupyter notebooks .NET Support in Jupyter notebooks
  • 38.
  • 41. About NimbusML • NimbusML provides state-of-the-art ML algorithms, transforms and components, aiming to make them useful for all developers, data scientists, and information workers and helpful in all products, services and devices. • The components are authored by the team members, as well as numerous contributors from MSR, CISL, Bing and other teams at Microsoft. • nimbusml is interoperable with scikit-learn estimators and transforms, while adding a suite of highly optimized algorithms written in C++ and C# for speed and performance.
  • 42. NimbusML Features NimbusML trainers and transforms support the following data structures for the fit() and transform() methods: • numpy.ndarray • scipy.sparse_cst • pandas.DataFrame. NimbusML also supports streaming from files without loading the dataset into memory, which allows training on data significantly exceeding memory using FileDataStream. • With FileDataStream, NimbusML is able to handle up to billion features and billions of training examples for select algorithms
  • 46. Clemente Giorio R&D Senior Software Engineer @ Deltatre ▪ Augmented/Mixed/Virtual Reality ▪ Artificial Intelligence, Machine Learning ▪ Internet of Things ▪ Embedded Apps ▪ Multimodal Tracking @tinux80 Author About us
  • 47. About us Ing. Gianni ROSA GALLINA R&D Senior Software Engineer @ Deltatre ▪ AI, Machine Learning, Deep Learning on multimedia content ▪ Virtual/Augmented/Mixed Reality ▪ Immersive video streaming & 3D graphics for sport events ▪ Cloud solutions, web backends, serverless, video workflows ▪ Mobile apps dev (Windows / Android / Xamarin) ▪ End-to-end solutions with Microsoft Azure @giannirg http://gianni.rosagallina.com Author