Operational Machine Learning
End-to-end ML for real-world applications
Most Machine Learning courses are given from the perspective of a Data Scientist and focus on the techniques and algorithms that allow to learn from data. This workshop takes the perspective of an application developer and instead provides an end-to-end view of ML integration into your applications. We’ll go all the way from data preparation to the integration of predictive models in your domain and their deployment in production.
The right mix of theory and hands-on work
The workshop is agnostic and features the best open source Python libraries (Pandas, scikit-learn, SKLL), APIs and ML-as-a-Service platforms (Microsoft Azure ML & Cortana Intelligence Suite, Amazon ML, BigML) for developers getting started in Machine Learning. It focuses on only two learning techniques, which turn out to be the most commonly used in practice: decision trees and ensembles.
Each workshop is 2 day long and comprises 8 modules of 3 blocks of 30’ each—including time for questions. Blocks are either Theory or Exercise, with at least one Exercise per module. The goal is to make you operational with machine learning at the end of the workshop.
What you will learn
- How Machine Learning works, its possibilities, its limitations, and the importance of data
- How to create, evaluate and deploy predictive models, via open source libraries, APIs and ML-as-a-Service platforms
- How to formulate ML problems that create value from data and that power predictive applications with innovative features
See workshop agenda for more details.
- Experience in programming and with the command line
- Attendees are expected to bring their own laptops for the hands-on practical work
- Basic knowledge of calculus, linear algebra, and probability theory will be useful for Theory in Modules 2, 4, 5 (see agenda)
This course is targeted to hackers, developers, software engineers and CTOs who are beginners in machine learning.
Each workshop will be given in a classroom setting with up to 20 participants.
Join now to avoid missing out!
Prices below do not include tax. We offer a very limited number of free registrations for job seekers and students. Learn more...
August 30 & 31, 2016 — Online
This edition of the workshop will be held online each day between 1pm and 4pm CEST. We will cover Modules 1 & 2 on August 30 and Modules 3 & 4 on August 31. A video recording will be made available after the workshop, so if you cannot attend live you will still be able to follow the workshop afterwards.
Coming soon: New York City, Paris, and more...
Get notified when more cities and dates are announced!
Day 1: Core ML
Module 1: Introduction to ML
- [Theory] Key ML concepts and terminology
- [Theory] Possibilities and use cases
- [Exercise] Formalizing an ML problem: credit scoring
Module 2: Model creation
Day 2: Going further with ML
Module 5: Model selection
- [Theory] Boosting predictions’ accuracy with ensembles
- [Exercise] Comparing models efficiently with SKLL
- [Theory] Cross-validation
Module 6: Data preparation
- [Theory] Limitations of ML
- [Exercise] Feature engineering on select use cases (priority inbox, real-estate price prediction, credit scoring, churn detection)
- [Exercise] Finding issues in data and fixing them in Pandas
Module 3: Operationalization
- [Theory] Functioning of REST APIs and importance for ML deployment in production
- [Exercise] Deploying your own models as scalable APIs with Microsoft Azure ML & Cortana Intelligence Suite, and querying them anywhere
- [Theory] Overview of ML-as-a-Service and Predictive API technologies (open source, proprietary and hybrid)
Module 4: Evaluation
Module 7: Advanced topics: Unsupervised Learning, Deep Learning and Recommender Systems
- [Exercise] Running automated clustering and anomaly detection with BigML’s API and interpreting results
- [Theory] Automatic feature extraction from text and images (illustrated with Indico’s Deep Learning API)
- [Theory] Building recommender systems by reduction to classification and collaborative filtering
Module 8: Developing your own use case
- [Theory] Formulating your own problem: asking the right questions and specifying key aspects of the problem with the Machine Learning Canvas
- [Exercise] Applying the Canvas to your own problem, or to credit scoring
- Conclusions: recap of key take-aways
Are there any differences between the online and in-person workshops?
Even though the online workshop is spread over two sessions taking place on two days, it only covers the first half of the agenda ("Day 1: Core ML"). Modules 1 and 2 will be given in the 1st session and Modules 3 and 4 will be given in the 2nd session.
Are there any special offers available?
Yes! Early-birds get 30% off of regular price. Students and job seekers can get free registration, but availability is very limited! Contact us.
I have another question
No prob! Contact us.
Can I ask questions during the online workshop?
Yep, if you’re attending live we’ll be taking questions at the end of every module. If you’re facing a specific problem related to one of the modules, feel free to prepare it in advance.
What if I can't watch live?
The next online workshop is on April 20 and April 21, 2016 between 8am and 11am PT, but don’t worry if you can’t make it on those days. Our focus is on making something that is valuable for a long time to come. You’ll get access to the workshop recording (so you can watch it at your leisure) as well as all the resources.