The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here

"Gradient Boosted Trees? Deep Learning? In less than 5 minutes? You Bet!"

IngoRMIngoRM Employee-RapidMiner, RapidMiner Certified Analyst, RapidMiner Certified Expert, Community Manager, RMResearcher, Member, University Professor Posts: 1,751 RM Founder
edited June 2019 in Knowledge Base

New Machine Learning Algorithms

We’ve added 4 new algorithms for machine learning, and I am still having a hard time figuring out which one I like the most:

  • Gradient Boosted Trees
  • Deep Learning
  • Generalized Linear Models
  • A brand-new implementation of Logistic Regression

Picture1


Naturally, I gave them a test run on some data sets, and was pretty freakin’ impressed with the prediction accuracy, automatic tuning capabilities, and runtimes.  On the well-known Sonar data set, for example, I consistently achieved performance results of 78% to 80% without any parameter tuning. This is a nice bump over other algorithms which only get up to 70% to 75% after heavy optimization circles.

 

This lift in performance can in part be attributed to the fact that these algorithms tune themselves. They are designed to find the best parameter settings for optimizing prediction accuracy.  This not only delivers better accuracy; but also reduces some of the effort required for tuning these bad boys.

 

You can find more on the RapidMiner blog at https://rapidminer.com/gradient-boosted-trees-deep-learning-less-5-minutes-bet/

 

Cheers,

Ingo

Tagged:
Sign In or Register to comment.