Random forest algorithm developed by CSB group featured at Keynote in Google I/O 2012 conference
The random forest algorithm developed by the Computational Systems Biology Research Group (CSB) at the Department of Signal Processing of Tampere University of Technology (TUT) was featured at the Keynote in Google I/O 2012 conference.RF-ACE algorithms, mainly developed by Timo Erkkilä from the Computational Systems Biology Research Group in collaboration with the Institute for Systems Biology in Seattle, USA, was used to demonstrate the new Google Compute Engine. The algorithm was scaled to run parallel on 600,000 cores across Google's global data centres. During the run, the Compute Engine performed between 1 and 10 quadrillion calculations per second, making it the third fastest computer in the world.
RF-ACE is an efficient implementation of a robust machine learning algorithm for uncovering multivariate associations from large and diverse data sets. RF-ACE natively handles numerical and categorical data with missing values. These features are essential for the analysis of heterogeneous biological datasets. RF-ACE was developed to uncover novel associations and insights into vast cancer datasets as a part of the Cancer Genome Atlas project.
More information:
https://developers.google.com/compute/io