Dr. Adín Ramírez Rivera will give his trial lecture in connection with the evaluation for an Associate Professor position of Image Analysis and Pattern Recognition / Machine Learning in the DSB group.
Title
Introduction to Unsupervised Representation Learning
Abstract
The amount of data that we generate nowadays is extensive. However, curating it is an expensive and time-consuming process. Unsupervised learning methods take advantage of this data by extracting patterns without needing explicit labels. In this lecture, we will introduce unsupervised representation learning. We will focus our discussion on autoencoders and their different formulations to learn without supervision. We will see some applications of these methods to images. Moreover, we will discuss advances and limitations in the research of unsupervised representations.
Short biography
Adín Ramírez Rivera received his B.Eng. degree in Computer Engineering from Universidad de San Carlos de Guatemala (USAC), Guatemala in 2009. He completed his M.Sc. and Ph.D. degrees in Computer Engineering from Kyung Hee University, South Korea in 2013. He is currently an Assistant Professor at the Institute of Computing, University of Campinas, Brazil. He is the Head of the Department of Infomation Systems at the Institute of Computing. His research interests are image and video understanding (including classification, semantic segmentation, feature modeling, and generation), and understanding and creating complex feature spaces.
Context
The candidate is invited to give a lecture to be suitable to be given in one of the courses IN5400 Machine Learning for Image Analysis or IN5520 Digital Image Analysis at master level.
Zoom connection
Please navigate to
to access the Zoom login information (requires login)