Mini-curso: Deep Convolutional Neural Networks: Foundations to Frontiers (Dr Nathan Jacobs)

Nestas duas semanas estamos recebendo a visita do Dr. Nathan Jacobs, da Universidade do Kentucky, com uma bolsa do PrInt.

Como parte das suas atividades o Dr. Jacobs apresentará um mini-curso sobre redes neurais convolucionais. Será nos dias 12 e 13 de março, quinta- e sexta-feira, entre as 9:30 e 12:00 em local a ser definido (mas nas instalações do INPE).

Inscrições devem ser feitas pelo link até 11/03/2020, 18:00!




Title: Deep Convolutional Neural Networks: Foundations to Frontiers


Over the past ten years, deep convolutional neural networks have emerged as an essential building block for the creation of state-of-the-art computer vision systems. While research challenges remain, today they can be easily incorporated into systems for a wide range of applications. They possess a unique combination of benefits that make this possible: they can be trained in an end-to-end manner, such that all parameters are optimized for the task; they are fast at inference time, without requiring sampling or other expensive inference steps; and the existing software tools enable the flexible integration of a wide variety of data types, often with very little custom code. This two-part course will cover foundations, both theoretical and practical, as well as the current state-of-the-art in computer vision research.


Dr. Nathan Jacobs earned a B.S. in Computer Science at the University of Missouri (1999) and a Ph.D. in Computer Science at Washington University in St. Louis (2010). Since then, he has been a Professor of Computer Science at the University of Kentucky, USA. He is the recipient of a National Science Foundation CAREER award in 2016 for his work at the intersection of computer vision, video surveillance, and remote sensing. During 2017-2018 he was a Visiting Research Scientist at Orbital Insight, Inc. where he developed methods for building detection and classification from satellite imagery. Dr. Jacobs’ research area is computer vision; his specialty is developing learning-based algorithms and systems for processing large-scale image collections. His current focus is on developing techniques for understanding the visual world from geotagged imagery, including images from social networks, publicly available outdoor webcams, and satellites. His research has been funded by the United States National Science Foundation (NSF), National Institutes of Health (NIH), Defense Advanced Research Projects Agency (DARPA), Intelligence Advanced Research Projects Activity (IARPA), National Geospatial-Intelligence Agency (NGA), Army Research Laboratory (ARL), Air Force Research Laboratory (AFRL), and Google.