![]() |
| |||||||||||||||
AutoML 2017 : Automatic Machine Learning Workshop (ICML 2017) | |||||||||||||||
Link: http://icml2017.automl.org | |||||||||||||||
| |||||||||||||||
Call For Papers | |||||||||||||||
The ICML 2017 Workshop on Automatic Machine Learning (AutoML)
10 August 2017, Co-located with ICML in Sydney, Australia Web: http://icml2017.automl.org Submission site: https://easychair.org/conferences/?conf=automl2017 Email: icml2017@automl.org _Important Dates (note that there are 2 submission deadlines)_ Submission deadline: 12 June 2017, 11:59pm UTC-12:00 (12 June anywhere in the world) Notification: 21 June 2017 Submission deadline (late breaking papers): 17 July 2017, 11:59pm UTC-12:00 Notification (late breaking papers): 28 July 2017 Workshop: 10 August 2017 __Workshop topic__ Machine learning has been very successful, but its successes rely on human machine learning experts to define the learning problem, select, collect and preprocess the training data, choose appropriate ML architectures (deep learning, random forests, SVMs, ...) and their hyperparameters, and finally evaluate the suitability of the learned models for deployment. As the complexity of these tasks is often beyond non-experts, the rapid growth of machine learning applications has created a demand for off-the-shelf machine learning methods that are more bullet-proof and can be used easily without expert knowledge. We call the resulting research area that targets progressive automation of machine learning AutoML. AutoML aims to automate many different stages of the machine learning process, and encourages contributions in any of the following (or related) areas: - Model selection, hyper-parameter optimization, and model search - Meta learning and transfer learning - Representation learning and automatic feature extraction / construction - Demonstrations (demos) of working AutoML systems - Automatic generation of workflows / workflow reuse - Automatic problem "ingestion" (from raw data and miscellaneous formats) - Automatic feature transformation to match algorithm requirements - Automatic detection and handling of skewed data and/or missing values - Automatic acquisition of new data (active learning, experimental design) - Automatic report writing (providing insight on automatic data analysis) - Automatic selection of evaluation metrics / validation procedures - Automatic selection of algorithms under time/space/power constraints - Automatic prediction post-processing and calibration - Automatic leakage detection - Automatic inference and differentiation - User interfaces for AutoML __Submission instructions__ We welcome original submissions up to 6 pages in JMLR Workshop and Proceedings format (not including references). In addition, we encourage submissions of previously-published material (clearly marked as such) that is closely related to the workshop topic. We especially encourage demos of working AutoML systems. Demos will be presented during the workshop as a short spotlight demo video and a live demonstration during the poster session. You can submit a demo proposal by submitting an accompanying paper describing the demo and a uploading a draft of your demo video. If accepted, you may of course change either before the workshop. Accepted original papers will be made available online and will be presented as posters and poster spotlight presentations at the workshop. The best 2-3 papers will be invited for oral plenary presentation. All other accepted papers will be presented as posters and short poster spotlight presentations. For submission details please see http://icml2017.automl.org. __Invited speakers__ - Hugo Larochelle, Google - Ameet Talwalkar, UCLA - Rich Caruana, Microsoft (conditional on attending ICML) - Himabindu Lakkaraju, Stanford (conditional on attending ICML) - Rob DeLine, Microsoft (conditional on attending ICML) Chairs: Joaquin Vanschoren, Roman Garnett Organizing committee: Pavel Brazdil, Christophe Giraud-Carrier, Isabelle Guyon, Frank Hutter, Balázs Kágl |
|