November tech meet — RapidMiner tutorial

The next BioGeeks tech meet will be on November 25th 2010 at UCL, where Andrew Clegg will be running a workshop entitled:

RapidMiner — machine learning for the rest of us

RapidMiner is an easy-to-use and feature-packed desktop app for machine learning, data & text mining, statistical analysis and visualization.

It allows you to build workflows for your experiments, easily swap learning algorithms and evaluation methods in and out, and compare and visualize the results. It also supports parallel processing and interfaces with databases, R and Weka, all from an intuitive graphical workbench. It includes modules for dozens of different classification, clustering and regression methods, along with dozens more handy pre-and post-processing tools.

The tutorial will take you through building a learning pipeline, training and tuning models in it, applying them to new data and comparing the results, using some well-known biological data.

Andrew will also demonstrate some methods for transforming and processing your input data in ways that would take hours to script by hand.

Bring a laptop if you want to follow along or just come to watch.

N.B. If you do bring a laptop, please install RapidMiner 5 Community Edition first, in case there’s a problem getting wifi on the day.

Where: Biochemistry Lecture Theatre, Darwin Building (basement), University College London

Enter campus via Malet Place opposite Waterstones, then turn left between the Engineering and DMS Watson buildings in square C4 of this map.

When: 6pm, Thursday 25 November 2010

Followed by drinks from 7:30ish at a venue to be decided on the day (depending on numbers).

Download a poster for this event here (PDF, 125K)

Duplicate of this post because of URL mix-up, all comments there please.


Comments are closed.