This workshop is designed specifically for developers looking to integrate Machine Learning into real-world applications and to create new value from data.
It provides an agnostic introduction to operational ML with open source and cloud platforms. It is the first ML workshop to go all the way from data preparation to the integration of predictive models in real-world applications and their deployment in production. Participants will learn to use Python open source libraries scikit-learn, Pandas and SKLL, and cloud platforms Microsoft Azure ML, Amazon ML, BigML and Indico (along with their APIs).
The workshop will be given in a classroom setting with up to 10 participants.
See workshop page for more details.
What you're getting
- Access to the workshop taking place on November 15 and 16, 2016 between 9.30am and 6pm (see venue information and address in the Registration Package)
- Resources, including slides, code and Jupyter notebooks
- A copy of Bootstrapping Machine Learning in pdf, epub and mobi formats
November 15: Core ML
- Module 1: Introduction to Machine Learning
- Module 2: Model creation
- Module 3: Operationalization
- Module 4: Evaluation
November 16: Going further with ML
- Module 5: Model selection
- Module 6: Data preparation
- Module 7: Advanced topics: Unsupervised Learning, Deep Learning and Recommender Systems
- Module 8: Developing your own use case
- 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.
Louis Dorard is General Chair of the PAPIs conferences, author of Bootstrapping Machine Learning, and an independent consultant. Louis holds a PhD in Machine Learning from University College London.
“Louis is an excellent teacher and you can feel how knowledgeable and passionate he is about this domain. I highly recommend this course!”
— Charles-Emmanuel Camus, Web Developer at Groupe Express-Roularta