Microsoft has released Automated ML technologies for developers through ML.NET, Azure ML Service, and Azure Databricks. This presenter is a data scientist and Microsoft architect, and will give a comprehensive overview of the utility and use case of this automated technology for production solutions. The presentation includes code you can try now.
Report
Share
Report
Share
1 of 44
Download to read offline
More Related Content
201909 Automated ML for Developers
1. Data and AI Scientist @ Microsoft
Cloud Solution Architect
US CTO Customer Success
@marktabnet
8. “It has exquisite buttons …
with long sleeves …works for
casual as well as business
settings”{f(x) {f(x)
Machine Learning
“Programming the UnProgrammable”
10. 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
12. 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
13. 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
15. 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
20. How much is this car worth?
Machine Learning Problem Example
21. Model Creation Is Typically Time-Consuming
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
22. 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
Model Creation Is Typically Time-Consuming
23. Which algorithm? Which parameters?Which features?
Iterate
Model Creation Is Typically Time-Consuming
24. Enter data
Define goals
Apply constraints
Output
Automated ML Accelerates Model Development
Input Intelligently test multiple models in parallel
Optimized model
25. Automated ML Capabilities
• Based on Microsoft Research
• Brain trained with several
million experiments
• Collaborative filtering and
Bayesian optimization
• Privacy preserving: No need
to “see” the data
26. Automated ML Capabilities
• ML Scenarios: Classification &
Regression, Forecasting
• Languages: Python SDK for
deployment and hosting for
inference – Jupyter notebooks
• Training Compute: Local
Machine, AML Compute, Data
Science Virtual Machine (DSVM),
Azure Databricks*
• Transparency: View run history,
model metrics, explainability*
• Scale: Faster model training
using multiple cores and parallel
experiments
* In Preview
28. Guardrails
Class imbalance
Train-Test split, CV, rolling CV
Missing value imputation
Detect high cardinality features
Detect leaky features
Detect overfitting
Model Interpretability / Feature Importance
36. Automated ML Customer Testimonials
• Press-coverage from
public preview:
• CNET
• VentureBeat
• PRNewswire
“I quite like your AutoML function. It gives me good results compared to
other libraries I tested before (tpot and auto-sklearn) that I believe was only
looking at scores and often gave me models that over-trained my data. And
of course the model from your suggested code is better.”
- Big oil company
“I will start with AutoML and use the algorithm that AutoML recommends to
further tune the model”
- Data Scientist
“I actually enjoy being able to use AutoML in a Jupyter notebook. The
DataRobot interface was nice for non-experts, but for someone like me, it
felt a bit basic.”
- Data Scientist