SlideShare a Scribd company logo
1 of 15
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Building machine learning models
automatically
Julien Simon
Global AI/ML Evangelist, AWS
@julsimon
AutoML
• AutoML aims at automating the process of building a model
• Problem identification: looking at the data set, what class of problem are
we trying to solve?
• Algorithm selection: which algorithm is best suited to solve the problem?
• Data preparation: how should data be prepared for best results?
• Hyperparameter tuning: what is the optimal set of training parameters?
Scenarios for AutoML
• Build models without any ML expertise
• Empower more people in your organization: software developers, business people
• Let experts focus on hard problems
• Experiment and build models at scale
• Thousands of data sets can be modeled without human intervention
• Let experts focus on new problems
• Automate 90% of the work, then tweak
• Data cleaning, feature engineering, feature selection, etc.
• Let experts focus on high value tasks such domain knowledge, and error analysis.
Transparency and control are important
• Get the best model only
• Hard to understand it
• Hard to reproduce it manually
• Get the best model, all candidates, full source code
• Understand how the model was built
• Keep tweaking for extra performance
Agenda
• Zero-code AutoML with SageMaker Studio
• AutoML with SageMaker AutoPilot and the SageMaker SDK
• Open source AutoML with AutoGluon
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon SageMaker helps you build, train, and deploy models
Fully managed data
processing jobs and
data labeling
workflows
Prepare
101011010
010101010
000011110
Collect and
prepare
training data
Build
One-click collaborative
notebooks and built-in,
high performance
algorithms and models
Choose or build an
ML algorithm
Web-based IDE for machine learning
Automatically build and train models
Train & Tune
One-click
training
Debugging and optimization Visually track and
compare experiments
Set up and manage
environments
for training
Train, debug, and
tune models
Manage training runs
Deploy & Manage
One-click
deployment and
auto scaling
Automatically
spot
concept drift
Fully
managed with
auto-scaling
for 75% less
Deploy
model in
production
Monitor
models
Add human
review of
predictions
Modular service and APIs, from experimentation to production
AutoML with Amazon SageMaker Autopilot
• SageMaker Autopilot covers all steps
• Problem identification: looking at the data set, what class of problem are we trying to solve?
• Algorithm selection: which algorithm is best suited to solve the problem?
• Data preprocessing: how should data be prepared for best results?
• Hyperparameter tuning: what is the optimal set of training parameters?
• Autopilot is fully transparent
• An auto-generated notebook shows you how models are built
• You can run it, reproduce the experiment, and keep tweaking
• Use cases: regression and classification, based on Linear Learner,
Factorization Machines, KNN, XGBoost
AutoML with Amazon SageMaker Autopilot
1. Upload the unprocessed dataset to S3
2. Configure the AutoML job
• Location of dataset
• Target attribute
• Completion criteria
3. Launch the job
4. View the list of candidates and the autogenerated notebook
5. Deploy the best candidate to a real-time endpoint, or use batch
transform
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Apache MXNet
• Open source software library for Deep Learning
• Natively implemented in C++
• Built-in support for many network architectures: FC, CNN, LSTM, etc.
• Symbolic API: Python, Scala, Clojure, R, Julia, Perl, Java (inference only)
• Imperative API: Gluon (Python), with computer vision, natural
language processing, and time series toolkits
AutoGluon
https://autogluon.mxnet.io/
• Open source AutoML toolkit
• Tabular data: regression, classification
• LightGBM, CatBoost, Random Forests, Extra Trees, KNN, linear regression
• Text data: classification
• Transfer learning based on Gluon NLP models
• Image data: classification, object detection
• Transfer learning based on Gluon CV models
• Built-in hyperparameter optimization
• Built-in ensemble prediction (bagging & stacking)
from autogluon import TabularPrediction as task
predictor = task.fit(train_data=task.Dataset(
file_path=TRAIN_DATA.csv),
label=COLUMN_NAME)
predictions = predictor.predict(
task.Dataset(file_path=TEST_DATA.csv))
AutoML on tabular data in 3 lines of code
Demo: AutoGluon on the Boston Housing Dataset
https://gitlab.com/juliensimon/dlnotebooks/-
/tree/master/autogluon
Getting started
http://aws.amazon.com/free
https://ml.aws
https://aws.amazon.com/sagemaker
https://github.com/aws/sagemaker-python-sdk
https://github.com/awslabs/amazon-sagemaker-examples
https://gitlab.com/juliensimon/dlnotebooks
https://youtube.com/juliensimonfr

More Related Content

What's hot

Quantum Computing with Amazon Braket
Quantum Computing with Amazon BraketQuantum Computing with Amazon Braket
Quantum Computing with Amazon Braket
Amazon Web Services
 
Amazon reInvent 2020 Recap: AI and Machine Learning
Amazon reInvent 2020 Recap:  AI and Machine LearningAmazon reInvent 2020 Recap:  AI and Machine Learning
Amazon reInvent 2020 Recap: AI and Machine Learning
Chris Fregly
 

What's hot (20)

Build, train, and deploy ML models at scale.pdf
Build, train, and deploy ML models at scale.pdfBuild, train, and deploy ML models at scale.pdf
Build, train, and deploy ML models at scale.pdf
 
An Introduction to Amazon SageMaker (October 2018)
An Introduction to Amazon SageMaker (October 2018)An Introduction to Amazon SageMaker (October 2018)
An Introduction to Amazon SageMaker (October 2018)
 
AIM410R Deep Learning Applications with TensorFlow, featuring Mobileye (Decem...
AIM410R Deep Learning Applications with TensorFlow, featuring Mobileye (Decem...AIM410R Deep Learning Applications with TensorFlow, featuring Mobileye (Decem...
AIM410R Deep Learning Applications with TensorFlow, featuring Mobileye (Decem...
 
Using Amazon SageMaker to build, train, & deploy your ML Models
Using Amazon SageMaker to build, train, & deploy your ML ModelsUsing Amazon SageMaker to build, train, & deploy your ML Models
Using Amazon SageMaker to build, train, & deploy your ML Models
 
Build Deep Learning Applications with TensorFlow & SageMaker
Build Deep Learning Applications with TensorFlow & SageMakerBuild Deep Learning Applications with TensorFlow & SageMaker
Build Deep Learning Applications with TensorFlow & SageMaker
 
Speed up your Machine Learning workflows with build-in algorithms
Speed up your Machine Learning workflows with build-in algorithmsSpeed up your Machine Learning workflows with build-in algorithms
Speed up your Machine Learning workflows with build-in algorithms
 
Quantum Computing with Amazon Braket
Quantum Computing with Amazon BraketQuantum Computing with Amazon Braket
Quantum Computing with Amazon Braket
 
Building serverless applications (April 2018)
Building serverless applications (April 2018)Building serverless applications (April 2018)
Building serverless applications (April 2018)
 
Machine Learning with Amazon SageMaker
Machine Learning with Amazon SageMakerMachine Learning with Amazon SageMaker
Machine Learning with Amazon SageMaker
 
Building smart applications with AWS AI services (October 2019)
Building smart applications with AWS AI services (October 2019)Building smart applications with AWS AI services (October 2019)
Building smart applications with AWS AI services (October 2019)
 
Machine Learning as a Service with Amazon Machine Learning
Machine Learning as a Service with Amazon Machine LearningMachine Learning as a Service with Amazon Machine Learning
Machine Learning as a Service with Amazon Machine Learning
 
Intro To Serverless Application Architecture: Collision 2018
Intro To Serverless Application Architecture: Collision 2018Intro To Serverless Application Architecture: Collision 2018
Intro To Serverless Application Architecture: Collision 2018
 
엔터프라이즈를 위한 머신러닝 그리고 AWS (김일호 솔루션즈 아키텍트, AWS) :: AWS Techforum 2018
엔터프라이즈를 위한 머신러닝 그리고 AWS (김일호 솔루션즈 아키텍트, AWS) :: AWS Techforum 2018엔터프라이즈를 위한 머신러닝 그리고 AWS (김일호 솔루션즈 아키텍트, AWS) :: AWS Techforum 2018
엔터프라이즈를 위한 머신러닝 그리고 AWS (김일호 솔루션즈 아키텍트, AWS) :: AWS Techforum 2018
 
Building Machine Learning models with Apache Spark and Amazon SageMaker | AWS...
Building Machine Learning models with Apache Spark and Amazon SageMaker | AWS...Building Machine Learning models with Apache Spark and Amazon SageMaker | AWS...
Building Machine Learning models with Apache Spark and Amazon SageMaker | AWS...
 
Amazon reInvent 2020 Recap: AI and Machine Learning
Amazon reInvent 2020 Recap:  AI and Machine LearningAmazon reInvent 2020 Recap:  AI and Machine Learning
Amazon reInvent 2020 Recap: AI and Machine Learning
 
MLops workshop AWS
MLops workshop AWSMLops workshop AWS
MLops workshop AWS
 
Machine Learning with Amazon SageMaker - Algorithms and Frameworks - BDA304 -...
Machine Learning with Amazon SageMaker - Algorithms and Frameworks - BDA304 -...Machine Learning with Amazon SageMaker - Algorithms and Frameworks - BDA304 -...
Machine Learning with Amazon SageMaker - Algorithms and Frameworks - BDA304 -...
 
Machine Learning: From Notebook to Production with Amazon Sagemaker
Machine Learning: From Notebook to Production with Amazon SagemakerMachine Learning: From Notebook to Production with Amazon Sagemaker
Machine Learning: From Notebook to Production with Amazon Sagemaker
 
AWS Machine Learning Week SF: End to End Model Development Using SageMaker
AWS Machine Learning Week SF: End to End Model Development Using SageMakerAWS Machine Learning Week SF: End to End Model Development Using SageMaker
AWS Machine Learning Week SF: End to End Model Development Using SageMaker
 
Machine Learning: From Notebook to Production with Amazon Sagemaker (April 2018)
Machine Learning: From Notebook to Production with Amazon Sagemaker (April 2018)Machine Learning: From Notebook to Production with Amazon Sagemaker (April 2018)
Machine Learning: From Notebook to Production with Amazon Sagemaker (April 2018)
 

Similar to Building Machine Learning Models Automatically (June 2020)

Similar to Building Machine Learning Models Automatically (June 2020) (20)

Costruisci modelli di Machine Learning con Amazon SageMaker Autopilot
Costruisci modelli di Machine Learning con Amazon SageMaker AutopilotCostruisci modelli di Machine Learning con Amazon SageMaker Autopilot
Costruisci modelli di Machine Learning con Amazon SageMaker Autopilot
 
AWS re:Invent 2018 - ENT321 - SageMaker Workshop
AWS re:Invent 2018 - ENT321 - SageMaker WorkshopAWS re:Invent 2018 - ENT321 - SageMaker Workshop
AWS re:Invent 2018 - ENT321 - SageMaker Workshop
 
Build, Train, and Deploy Machine Learning for the Enterprise with Amazon Sage...
Build, Train, and Deploy Machine Learning for the Enterprise with Amazon Sage...Build, Train, and Deploy Machine Learning for the Enterprise with Amazon Sage...
Build, Train, and Deploy Machine Learning for the Enterprise with Amazon Sage...
 
AIM361 Optimizing machine learning models with Amazon SageMaker (December 2019)
AIM361 Optimizing machine learning models with Amazon SageMaker (December 2019)AIM361 Optimizing machine learning models with Amazon SageMaker (December 2019)
AIM361 Optimizing machine learning models with Amazon SageMaker (December 2019)
 
201909 Automated ML for Developers
201909 Automated ML for Developers201909 Automated ML for Developers
201909 Automated ML for Developers
 
Introduction to ML.NET
Introduction to ML.NETIntroduction to ML.NET
Introduction to ML.NET
 
Machine learning
Machine learningMachine learning
Machine learning
 
Integrate Machine Learning into Your Spring Application in Less than an Hour
Integrate Machine Learning into Your Spring Application in Less than an HourIntegrate Machine Learning into Your Spring Application in Less than an Hour
Integrate Machine Learning into Your Spring Application in Less than an Hour
 
201906 02 Introduction to AutoML with ML.NET 1.0
201906 02 Introduction to AutoML with ML.NET 1.0201906 02 Introduction to AutoML with ML.NET 1.0
201906 02 Introduction to AutoML with ML.NET 1.0
 
The Power of Auto ML and How Does it Work
The Power of Auto ML and How Does it WorkThe Power of Auto ML and How Does it Work
The Power of Auto ML and How Does it Work
 
[AWS Innovate 온라인 컨퍼런스] 간단한 Python 코드만으로 높은 성능의 기계 학습 모델 만들기 - 김무현, AWS Sr.데이...
[AWS Innovate 온라인 컨퍼런스] 간단한 Python 코드만으로 높은 성능의 기계 학습 모델 만들기 - 김무현, AWS Sr.데이...[AWS Innovate 온라인 컨퍼런스] 간단한 Python 코드만으로 높은 성능의 기계 학습 모델 만들기 - 김무현, AWS Sr.데이...
[AWS Innovate 온라인 컨퍼런스] 간단한 Python 코드만으로 높은 성능의 기계 학습 모델 만들기 - 김무현, AWS Sr.데이...
 
MLOPS By Amazon offered and free download
MLOPS By Amazon offered and free downloadMLOPS By Amazon offered and free download
MLOPS By Amazon offered and free download
 
AWS reinvent 2019 recap - Riyadh - AI And ML - Ahmed Raafat
AWS reinvent 2019 recap - Riyadh - AI And ML - Ahmed RaafatAWS reinvent 2019 recap - Riyadh - AI And ML - Ahmed Raafat
AWS reinvent 2019 recap - Riyadh - AI And ML - Ahmed Raafat
 
End-to-End Machine Learning with Amazon SageMaker
End-to-End Machine Learning with Amazon SageMakerEnd-to-End Machine Learning with Amazon SageMaker
End-to-End Machine Learning with Amazon SageMaker
 
From Notebook to production with Amazon SageMaker
From Notebook to production with Amazon SageMakerFrom Notebook to production with Amazon SageMaker
From Notebook to production with Amazon SageMaker
 
Simplifying AI and Machine Learning with Watson Studio
Simplifying AI and Machine Learning with Watson StudioSimplifying AI and Machine Learning with Watson Studio
Simplifying AI and Machine Learning with Watson Studio
 
Introducing Amazon SageMaker
Introducing Amazon SageMakerIntroducing Amazon SageMaker
Introducing Amazon SageMaker
 
MLOps with serverless architectures (October 2018)
MLOps with serverless architectures (October 2018)MLOps with serverless architectures (October 2018)
MLOps with serverless architectures (October 2018)
 
Building, Training, and Deploying fast.ai Models Using Amazon SageMaker (AIM4...
Building, Training, and Deploying fast.ai Models Using Amazon SageMaker (AIM4...Building, Training, and Deploying fast.ai Models Using Amazon SageMaker (AIM4...
Building, Training, and Deploying fast.ai Models Using Amazon SageMaker (AIM4...
 
Azure Machine Learning Dotnet Campus 2015
Azure Machine Learning Dotnet Campus 2015 Azure Machine Learning Dotnet Campus 2015
Azure Machine Learning Dotnet Campus 2015
 

More from Julien SIMON

More from Julien SIMON (20)

An introduction to computer vision with Hugging Face
An introduction to computer vision with Hugging FaceAn introduction to computer vision with Hugging Face
An introduction to computer vision with Hugging Face
 
Reinventing Deep Learning
 with Hugging Face Transformers
Reinventing Deep Learning
 with Hugging Face TransformersReinventing Deep Learning
 with Hugging Face Transformers
Reinventing Deep Learning
 with Hugging Face Transformers
 
Building NLP applications with Transformers
Building NLP applications with TransformersBuilding NLP applications with Transformers
Building NLP applications with Transformers
 
Starting your AI/ML project right (May 2020)
Starting your AI/ML project right (May 2020)Starting your AI/ML project right (May 2020)
Starting your AI/ML project right (May 2020)
 
Scale Machine Learning from zero to millions of users (April 2020)
Scale Machine Learning from zero to millions of users (April 2020)Scale Machine Learning from zero to millions of users (April 2020)
Scale Machine Learning from zero to millions of users (April 2020)
 
An Introduction to Generative Adversarial Networks (April 2020)
An Introduction to Generative Adversarial Networks (April 2020)An Introduction to Generative Adversarial Networks (April 2020)
An Introduction to Generative Adversarial Networks (April 2020)
 
A pragmatic introduction to natural language processing models (October 2019)
A pragmatic introduction to natural language processing models (October 2019)A pragmatic introduction to natural language processing models (October 2019)
A pragmatic introduction to natural language processing models (October 2019)
 
Build, train and deploy ML models with SageMaker (October 2019)
Build, train and deploy ML models with SageMaker (October 2019)Build, train and deploy ML models with SageMaker (October 2019)
Build, train and deploy ML models with SageMaker (October 2019)
 
The Future of AI (September 2019)
The Future of AI (September 2019)The Future of AI (September 2019)
The Future of AI (September 2019)
 
Deep Learning on Amazon Sagemaker (July 2019)
Deep Learning on Amazon Sagemaker (July 2019)Deep Learning on Amazon Sagemaker (July 2019)
Deep Learning on Amazon Sagemaker (July 2019)
 
Build, train and deploy ML models with Amazon SageMaker (May 2019)
Build, train and deploy ML models with Amazon SageMaker (May 2019)Build, train and deploy ML models with Amazon SageMaker (May 2019)
Build, train and deploy ML models with Amazon SageMaker (May 2019)
 
Build, train and deploy Machine Learning models on Amazon SageMaker (May 2019)
Build, train and deploy Machine Learning models on Amazon SageMaker (May 2019)Build, train and deploy Machine Learning models on Amazon SageMaker (May 2019)
Build, train and deploy Machine Learning models on Amazon SageMaker (May 2019)
 
Become a Machine Learning developer with AWS services (May 2019)
Become a Machine Learning developer with AWS services (May 2019)Become a Machine Learning developer with AWS services (May 2019)
Become a Machine Learning developer with AWS services (May 2019)
 
Scaling Machine Learning from zero to millions of users (May 2019)
Scaling Machine Learning from zero to millions of users (May 2019)Scaling Machine Learning from zero to millions of users (May 2019)
Scaling Machine Learning from zero to millions of users (May 2019)
 
Become a Machine Learning developer with AWS (Avril 2019)
Become a Machine Learning developer with AWS (Avril 2019)Become a Machine Learning developer with AWS (Avril 2019)
Become a Machine Learning developer with AWS (Avril 2019)
 
Solve complex business problems with Amazon Personalize and Amazon Forecast (...
Solve complex business problems with Amazon Personalize and Amazon Forecast (...Solve complex business problems with Amazon Personalize and Amazon Forecast (...
Solve complex business problems with Amazon Personalize and Amazon Forecast (...
 
Build, Train and Deploy Machine Learning Models at Scale (April 2019)
Build, Train and Deploy Machine Learning Models at Scale (April 2019)Build, Train and Deploy Machine Learning Models at Scale (April 2019)
Build, Train and Deploy Machine Learning Models at Scale (April 2019)
 
Optimize your Machine Learning workloads (April 2019)
Optimize your Machine Learning workloads (April 2019)Optimize your Machine Learning workloads (April 2019)
Optimize your Machine Learning workloads (April 2019)
 
Build Machine Learning Models with Amazon SageMaker (April 2019)
Build Machine Learning Models with Amazon SageMaker (April 2019)Build Machine Learning Models with Amazon SageMaker (April 2019)
Build Machine Learning Models with Amazon SageMaker (April 2019)
 
Deep Learning with Tensorflow and Apache MXNet on AWS (April 2019)
Deep Learning with Tensorflow and Apache MXNet on AWS (April 2019)Deep Learning with Tensorflow and Apache MXNet on AWS (April 2019)
Deep Learning with Tensorflow and Apache MXNet on AWS (April 2019)
 

Recently uploaded

+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
?#DUbAI#??##{{(☎️+971_581248768%)**%*]'#abortion pills for sale in dubai@
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
vu2urc
 

Recently uploaded (20)

From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of Brazil
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your Business
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdf
 
HTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesHTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation Strategies
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 

Building Machine Learning Models Automatically (June 2020)

  • 1. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. Building machine learning models automatically Julien Simon Global AI/ML Evangelist, AWS @julsimon
  • 2. AutoML • AutoML aims at automating the process of building a model • Problem identification: looking at the data set, what class of problem are we trying to solve? • Algorithm selection: which algorithm is best suited to solve the problem? • Data preparation: how should data be prepared for best results? • Hyperparameter tuning: what is the optimal set of training parameters?
  • 3. Scenarios for AutoML • Build models without any ML expertise • Empower more people in your organization: software developers, business people • Let experts focus on hard problems • Experiment and build models at scale • Thousands of data sets can be modeled without human intervention • Let experts focus on new problems • Automate 90% of the work, then tweak • Data cleaning, feature engineering, feature selection, etc. • Let experts focus on high value tasks such domain knowledge, and error analysis.
  • 4. Transparency and control are important • Get the best model only • Hard to understand it • Hard to reproduce it manually • Get the best model, all candidates, full source code • Understand how the model was built • Keep tweaking for extra performance
  • 5. Agenda • Zero-code AutoML with SageMaker Studio • AutoML with SageMaker AutoPilot and the SageMaker SDK • Open source AutoML with AutoGluon
  • 6. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 7. Amazon SageMaker helps you build, train, and deploy models Fully managed data processing jobs and data labeling workflows Prepare 101011010 010101010 000011110 Collect and prepare training data Build One-click collaborative notebooks and built-in, high performance algorithms and models Choose or build an ML algorithm Web-based IDE for machine learning Automatically build and train models Train & Tune One-click training Debugging and optimization Visually track and compare experiments Set up and manage environments for training Train, debug, and tune models Manage training runs Deploy & Manage One-click deployment and auto scaling Automatically spot concept drift Fully managed with auto-scaling for 75% less Deploy model in production Monitor models Add human review of predictions Modular service and APIs, from experimentation to production
  • 8. AutoML with Amazon SageMaker Autopilot • SageMaker Autopilot covers all steps • Problem identification: looking at the data set, what class of problem are we trying to solve? • Algorithm selection: which algorithm is best suited to solve the problem? • Data preprocessing: how should data be prepared for best results? • Hyperparameter tuning: what is the optimal set of training parameters? • Autopilot is fully transparent • An auto-generated notebook shows you how models are built • You can run it, reproduce the experiment, and keep tweaking • Use cases: regression and classification, based on Linear Learner, Factorization Machines, KNN, XGBoost
  • 9. AutoML with Amazon SageMaker Autopilot 1. Upload the unprocessed dataset to S3 2. Configure the AutoML job • Location of dataset • Target attribute • Completion criteria 3. Launch the job 4. View the list of candidates and the autogenerated notebook 5. Deploy the best candidate to a real-time endpoint, or use batch transform
  • 10. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 11. Apache MXNet • Open source software library for Deep Learning • Natively implemented in C++ • Built-in support for many network architectures: FC, CNN, LSTM, etc. • Symbolic API: Python, Scala, Clojure, R, Julia, Perl, Java (inference only) • Imperative API: Gluon (Python), with computer vision, natural language processing, and time series toolkits
  • 12. AutoGluon https://autogluon.mxnet.io/ • Open source AutoML toolkit • Tabular data: regression, classification • LightGBM, CatBoost, Random Forests, Extra Trees, KNN, linear regression • Text data: classification • Transfer learning based on Gluon NLP models • Image data: classification, object detection • Transfer learning based on Gluon CV models • Built-in hyperparameter optimization • Built-in ensemble prediction (bagging & stacking)
  • 13. from autogluon import TabularPrediction as task predictor = task.fit(train_data=task.Dataset( file_path=TRAIN_DATA.csv), label=COLUMN_NAME) predictions = predictor.predict( task.Dataset(file_path=TEST_DATA.csv)) AutoML on tabular data in 3 lines of code
  • 14. Demo: AutoGluon on the Boston Housing Dataset https://gitlab.com/juliensimon/dlnotebooks/- /tree/master/autogluon

Editor's Notes

  1. Amazon SageMaker is a fully managed service that removes the heavy lifting from each step of the machine learning process. Since launch, AWS has regularly added new capabilities to Amazon SageMaker, with more than 50 new capabilities delivered over the past 12 months. These capabilities have helped many more developers build custom machine learning models. But just as barriers to machine learning adoption have been removed by Amazon SageMaker, customer desire to utilize machine learning at scale has only increased. Amazon SageMaker makes a lot of the steps required to develop great machine learning models much easier. Amazon SageMaker brings lots of tools together through an IDE so you can test, debug, deployment, monitoring, and profile all within a single environment. With Amazon SageMaker, you have the flexibility to use automated machine learning or use any component as a modular capability.