Professional Documents
Culture Documents
Automlmicrosoftazure 1625847967437
Automlmicrosoftazure 1625847967437
Axel Sirota
Introduction
What are we going to do?
Introduction
AutoML in the SDK
• Who am I?
• SDK vs Studio
• What is AutoML?
• Feature Engineering in the SDK
• What does it solve?
• Interpreting results
• Who am I?
• SDK vs Studio
• What is AutoML?
• Feature Engineering in the SDK
• What does it solve?
• Interpreting results
QR to my
Pluralsight courses
– Microsoft Certified Trainer
QR to my
– Microsoft Certified Trainer Pluralsight courses
- None
- Heard of it in conferences but no usage
- POCs but no production experience
- Production experience
A Case Study: Creating an ML
model
Which features to
engineer?
A Case Study: Creating an ML
model
Which model/
Which features to
architecture to
engineer?
use?
A Case Study: Creating an ML
model
Which model/
Which features to Which parameters
architecture to
engineer? to use?
use?
A Case Study: Creating an ML
model
Which model/ Which
Which features to Which parameters
architecture to hyperparameters
engineer? to use?
use? to use?
A Case Study: Creating an ML
model
Which model/ Which
Which features to Which parameters
architecture to hyperparameters
engineer? to use?
use? to use?
Basic Neural
Network
A Case Study: Creating an ML
model
Optimal
Basic Neural
AutoML architecture and
Network
hyperparameters
A Case Study: Creating an ML
model
Optimal
Basic Neural
AutoML architecture and
Network
hyperparameters
• Who am I?
• SDK vs Studio
• What is AutoML?
• Feature Engineering in the SDK
• What does it solve?
• Interpreting results
Raw Data
Data
Cleaning
Machine Learning Workflow
Feature
Raw Data
Selection
Data Feature
Cleaning Construction
Feature
Preprocessing
Machine Learning Workflow
Feature
Raw Data
Selection
Feature
Preprocessing
Machine Learning Workflow
Feature
Raw Data
Selection
Feature
Preprocessing
Machine Learning Workflow
Feature
Raw Data
Selection
Feature
Preprocessing
Trained
Model
Machine Learning Workflow
Feature
Raw Data
Selection
Feature
Preprocessing
Trained
AutoML Model
Why AutoML?
Default
parameters are
“always” bad
Why AutoML?
Default
“Best” model
parameters are
is a surprise
“always” bad
Why AutoML?
Data cleaning
Default
“Best” model and feature
parameters are
is a surprise extraction time
“always” bad
Default
Parameters
Image Source: “Data-driven advice for applying machine learning to bioinformatics problems”
Best
model
Image Source: “Data-driven advice for applying machine learning to bioinformatics problems”
Data cleaning time
AutoML in the Studio
Validating our model
Cross Validation
Cross Validation
The Pipeline
Model Scores Model 1
Best model
Test set
Model Scores Model 2
True
Best model performance
Model Scores Model 3 best model
Inputting Dropping
Scaling and Normalisation
Source: “Minute-Scale Wind Speed Forecasting Using Scanning Lidar Inflow Measurements” Simon et. at. 2018
Rolling Windows
Date Load
2021-01-01 4500
2021-01-02 4650
2021-01-03 4400
2021-01-04 4100
Rolling Windows
Date Load Load + 2
2021-01-03 4400
2021-01-04 4100
Rolling Windows
Date Load
2021-01-01 4500
2021-01-02 None
2021-01-03 4400
2021-01-04 4100
Rolling Windows
Date Load
2021-01-01 4500
2021-01-03 4400
2021-01-04 4100
Exercise Time
Live Demo: Adding Feature Engineering to an
AutoML Experiment from the SDK
Axel Sirota