KDnuggets Home » News » 2015 » Jan » News, Features » ChaLearn Automatic Machine Learning Challenge (AutoML) ( 15:n03 )

ChaLearn Automatic Machine Learning Challenge (AutoML)


Design the perfect machine learning “black box” capable of performing all model selection and hyper-parameter tuning without any human intervention. There is a prize pool of $30,000 donated by Microsoft if you are willing to make your code publicly available.



By Isabelle Guyon.

ChaLearn Automatic Machine Learning Challenge (AutoML)

Five rounds until June 2015
First deadline February 14 (Tweakathon 0: submit results on sample datasets; AutoML 1: submit code to solve binary classification problems)

Design the perfect machine learning “black box” capable of performing all model selection and hyper-parameter tuning without any human intervention.
AutoML
We are progressively introducing 30 classification and regression tasks, with datasets pre-formatted in feature representations. There is a broad diversity of data types and distributions and the problems are drawn from a wide variety of domains and include medical diagnosis from laboratory analyses, speech recognition, credit rating, prediction or drug toxicity or efficacy, classification of text, prediction of customer satisfaction, object recognition, protein structure prediction, action recognition in video data, etc. While there exist machine learning toolkits including methods that can solve all these problems, it is still considerable human effort to find, for a given combination of dataset, task, metric of evaluation, and available computational time, the combination of methods and hyper-parameter setting that is best suited.

There is a prize pool of $30,000 donated by Microsoft if you are willing to make your code publicly available. No condition on releasing code or algorithms to just enter the challenge.



Related:

Sign Up