Machine learning hands-on: making good predictions from many bad ones
Hosted by OsloFSharp
Details
Making bad predictions is pretty easy. But what if you could find a way to take many simple and mediocre prediction models, and combine them into a meta-model that works better than the sum of its individual parts? This question is the focus of what Machine Learning people call Ensemble Methods.
In this hands-on session, we will attempt to determine if a bottle of wine is good or terrible, by exploring one of these techniques (boosting), looking at where our predictions go wrong, and making progressive adjustments.
This session is beginners-friendly; no prior knowledge of F# or Machine Learning is required. We will take a real dataset, and progressively write a model from the ground up, in F#, using only very simple building blocks - and afterwards you'll be able to impress your colleagues and friends by using words such as "Gradient Boosting" :slightly_smiling_face:
Pre-requisites: come with a laptop with F# installed (see fsharp.org for instructions), and a development environment ready to go. We will be using scripts only, VS Code + Ionide is enough.
Presenters:
Mathias Brandewinder has been developing software for about 10 years, and loving every minute of it, except maybe for a few release days. His language of choice was C#, until he discovered F# and fell in love with it. He enjoys arguing about code and how to make it better, and gets very excited when discussing TDD or functional programming. His other professional interests include machine learning and applied math. Mathias is a Microsoft F# MVP, author of "Machine Learning Projects for .NET Developers" (Apress), and the founder of Clear Lines Consulting. He is based in San Francisco, blogs at http://www.brandewinder.com , and can be found on Twitter as @brandewinder (https://twitter.com/brandewinder).
Evelina Gabasova (@evelgab (https://twitter.com/evelgab)) is a machine learning researcher working in bioinformatics, trying to reverse-engineer cancer using computational methods. She is also an international conference speaker and enjoys giving talks on all topics data science. Currently, Evelina does most of her programming in R and F#, and got awarded the Microsoft MVP award for her work in the F# community. She originally started as a programmer but got interested in machine learning early on and did a mathematics PhD at the University of Cambridge, where she developed new statistical methods to analyze complex biomedical datasets.
Agenda:
18:00 -> 18:30 - Food
18:30 -> 20:00 - Workshop
20:00 -> ... - Geekbeer
