Workshop

CANCELED

Scope and motivations:

Machine learning has achieved considerable successes and an ever growing number of disciplines rely on it. However, this success crucially relies on human machine learning experts, who select appropriate features, workflows, machine learning paradigms, algorithms, and hyperparameters. As the complexity of these tasks is often beyond non-experts, the rapid growth of machine learning has created a demand for off-the-shelf machine learning methods that can be used easily and without expert knowledge. We call the resulting research area that targets progressive automation of machine learning AutoML. The results of the AutoML challenge http://codalab.org/AutoML, which is an accepted IJCNN 2015 competition, will be discussed in the workshop. But the workshop will be an interdisciplinary forum open to all and acknowledged experts in the fields will be invited to speak.

Topics:

AutoML aims to automate many different stages of the machine learning process, such as:

● Natural and artificial systems capable of autonomous learning

● Model selection, hyperparameter optimization, and model search

● Representation learning and automatic feature extraction / construction

● Reusable workflows and automatic generation of workflows

● Meta learning and transfer learning

● Automatic problem "ingestion" (from raw data and miscellaneous formats)

● Automatically detecting and handling skewed data, missing values, leakage detection and prevention

● Matching problems to methods/algorithms

● Automatic acquisition of new data (active learning, experimental design)

● Automatic report writing (providing insight on the data analysis performed automatically)

● User interfaces for AutoML (e.g., “Turbo Tax for Machine Learning”)

● Automatic creation of appropriately sized and stratified train, validation, and test sets

● Automatic selection of algorithms to satisfy time/space/power constraints at traintime or at runtime

● Life long autonomous machine learning

Call for abstracts:

Please submit 200 word abstracts on the above topics before April 30, 2015 to automl@chalearn.org.

Organizers:

Isabelle Guyon, ChaLearn, Berkeley, USA

Evelyne Viegas, Microsoft, Redmond, USA