Deep Learning for Multimedia Data: Teaching Computers to Sense
Omar Florez$^{1}$
$^{1}$Intel Labs. California USA
Schedule:Wed 21st@09:00, Room: A

For the past few years, deep learning has been making rapid progress in both techniques and applications; significant performance gains were reported using deep learning in automatic speech recognition and image recognition over hand-optimized feature representations.

Advances in smartphones, tablets, and wearables have made possible to sense a rich collection of user data, examples include audio, images, and video. This information allows us to infer user contexts such as faces, semantic locations, activities, and mood states enabling better and personalized user experiences. This explains the growing interest of industry (Intel, Facebook, Google, NVIDIA, Spotify, Netflix, Baidu, etc.) trying to take advantage of deep learning capabilities in recent years.

In several image and speech tasks, the success of deep learning is due to its ability to learn representations from noisy and unstructured data. Context sensing faces the same problem therefore we believe applications of deep learning in this domain can be advantageous. During this talk we will try bringing together researchers and applicants to discuss some of the deep learning algorithms and capabilities for multimedia and context domains as well as explore possible new research areas.

Short Biography Dr. Omar U. Florez is a Research Scientist at the Anticipatory Computing Group at Intel Labs (California, USA). He graduated from Universidad Nacional de San Agustin, Peru in 2007 and received his Ph.D. in Computer Science at Utah State University in 2013. He is a recipient of an Innovation Award on Large-Scale Analytics by IBM Research, and the organizer of the NSF-funded Broader Participation in Data Mining workshop at KDD in 2014, which for first time funded the attendance of under-represented researchers worldwide. He is also the co-founder of South Americans in Computing. Dr. Florez's research interests cover statistical machine learning, recommender systems, and deep learning for multimedia data. He has 20+ academic publications and journals in ACM, IEEE, and Springer.


	author 		= {Omar Florez},
	title 		= {Deep Learning for Multimedia Data: Teaching Computers to Sense},
	booktitle 	= {2015 XLI Latin American Computing Conference (CLEI), Special Edition},
	pages 		= {3--3},
	year 		= {2015},
	editor 		= {Universidad Católica San Pablo},
	address 	= {Arequipa-Peru},
	month 		= {October},
	organization 	= {CLEI},
	publisher 	= {CLEI},
	url 		= {},
	isbn 		= {978-9972-825-91-0},

Generated by Ernesto Cuadros-Vargas , Sociedad Peruana de Computación-Peru, Universidad Católica San Pablo, Arequipa-Perú