AIL 2012 - Workshop on Active and Incremental Learning

This workshop aims to offer a meeting opportunity for academics and industry-related researchers, belonging to the various communities of Computational Intelligence, Machine Learning, Experimental Design and Data Mining to discuss new areas of active and incremental learning, and to bridge the gap between data acquisition or experimentation and model building. How active sampling, incremental learning and data acquisition, can contribute towards the design and modelling of highly intelligent autonomous learning systems?
Example 1: Imagine a simple problem which is to supervise a node in a telecommunication network using a binary classifier. The first step is to train incrementally (and perhaps using active learning) the classifier using a data stream and then to maintain this classifier without any “human” interaction. The classifier has to be completely autonomous. Papers which will propose new elements to go to this direction will be in the scope of the workshop.
Example 2: The diachronic analysis of a large and evolving information source for detecting stable, emerging or vanishing topics could be done with the help of clustering methods. However, to provide satisfying detection accuracy, the exploited methods must altogether deal with the plasticity stability dilemma and be able to manage an evolving data description space. Paper that will propose efficient solutions that respect these constraints will be also in the scope of the workshop.
Topics of interest to the workshop include (but are not limited to):
Experimental Design
Active Learning
Autonomous Learning
Incremental Learning
Autonomous intelligent systems
On-line learning
Novelty and Drift Detection
Adaptive clustering methods
Case Studies of AIL Learning (railway stations, airport, bank branches, etc)
Autonomous Robots
Importantes dates:
28 May 2012: Workshop paper submission deadline
28 Jun 2012: Notification of acceptance
15 Jul 2012: Camera-ready version deadline
August 27 or 28, 2012: Workshop