Introduction to Artificial Intelligence: Deep Learning and Attention Mechanisms
SUMMARY
This talk introduces artificial intelligence and deep learning. The basic concepts underlying convolutional and recurrent neural networks are presented. A recent alternative model based on attention mechanisms (transformers) is also introduced. Applications of these methods to image processing and time series in astronomy and medicine are illustrated.
PRESENTS
Pablo Estévez received the professional degree of Civil Electrical Engineer from the University of Chile in 1981, and the Master's and Ph.D. degrees in Information Engineering from the University of Tokyo, Japan, in 1992 and 1995, respectively. He is a full professor of the Electrical Engineering Department of the University of Chile, and a former director of this same Department in the period 2006-2010. Prof. Estévez is IEEE Fellow and was President of the IEEE Computational Intelligence Society (IEEE Computational Intelligence Society: CIS) for the period 2016-2017. He is currently an Associate Editor of the IEEE Transactions on Artificial Intelligence journal. He has been awarded the 2019 IEEE CIS Meritorious Service Award and 2019 IEEE Latin-America Eminent Engineer Award. He was chair of the International Joint Conference on Neural Networks (IJCNN), held in July 2016, in Vancouver, Canada, and co-chair of the 2018 IEEE World Congress on Computational Intelligence, held in Rio de Janeiro, Brazil, in July 2018. He is a Research Associate at the Millennium Institute for Astrophysics (2014-2023) and holds two US patents. He is also co-author of more than 150 journal and conference papers (Google Scholar h-index = 30). In the last 5 years, Prof. Estevez has been working on the theory and application of deep learning, including convolutional neural networks and recurrent neural networks, techniques that are at the core of current artificial intelligence.
WHEN & WHERE
Wednesday, September 22 at 3:00 p.m.
Zoom link: https://bit.ly/DSUAI2109