C26: Learning with Uncertainty

Paper Submission for C26

SMC2018:C26 submission site (external site)

Abstracts

Uncertainty exists in almost every learning problem, especially in big data and non-stationary environments. Uncertainty may come from data collection, data cleaning, data normalization, noise, randomness in algorithm, etc. With the exponential growth of video, images, and diversified types of data being involved in highly complicated machine learning tasks, dealing with uncertainty in data, learning algorithm, and other sources is important to the success of those learning tasks. This special session aims to provide a forum for researchers to demonstrate, discuss, and exchange new idea on learning with uncertainty. Topics of interests include but not limited to fuzzy methods, neural networks, deep learning models, generalization error models, and their applications in important applications with uncertainties.

Session Chairs