Applications of Machine Learning in Multimedia

March 7, 2014, 11 AM

302- 308



As we enter the age of big data, necessary automation of data analysis can be accomplished with the development of various machine-learning methods. Since the landmark development of the Vapnik-Chervonenkis theory, which is an attempt to explain the learning process from a statistical point of view, machine learnings commitment to improve generalization through regularization and prior probability assumption and also to simplify and visualize the working environment with a probabilistic graphical model have attracted the attention of many researchers and have so far made great impact in many areas including bioinformatics, computer vision, robotics, finance, brain modeling.

This talk will introduce several machine learning application embracing large-margin theory, Bayesian inference, Deep Learning architectures such as Sum Product Node, Gaussian Process, discriminative dictionary learning in performing various tasks involving recognition and understanding of multimedia.