The Deep Learning 2.0 program is a multi-year A*STAR AI program, focused on capturing the next wave of deep learning.
The program is focused on
(a) 10x open problems in deep learning algorithmic research: thrusts include learning with 10x fewer labeled samples, compressing networks by 100x, incorporating knowledge graphs into deep learning, online deep learning, and white-box deep learning.
(b) Next generation hardware for deep learning: we are looking beyond GPUs and TPUs, and reimagining the entire hardware stack for deep learning from algorithms all the way down to silicon
(c) New emerging enterprise applications for deep learning: ranging from personalized medicine, finance, health-care, IoT and advanced semiconductor manufacturing.
(d) Deep learning on encrypted data: the challenges lying at the intersection of deep learning and homomorphic encryption in making this technology closer to adoption
I will provide an overview of the program
Vijay Chandrasekhar leads AI at the Institute for Infocomm Research. He completed his B.S and M.S. from Carnegie Mellon University (2002-2005), and Ph.D. in Electrical Engineering from Stanford University (2006-2013). His research contributions span deep learning and machine learning algorithms, computer vision, large-scale image and audio search, augmented reality and deep learning hardware. He has published more than 100 papers/MPEG contributions in a wide range of top-tier journals/conferences like IJCV, ICCV, CVPR, SPM, ACM MM, TIP, DCC, ISMIR, ICLR, ICDM etc, and has filed 7 US patents (4 granted, 3 pending). His Ph.D. work on feature compression led to the widely adopted MPEG-CDVS (Compact Descriptors for Visual Search) standard, which he actively contributed from 2010-2013. He was awarded the A*STAR National Science Scholarship (NSS) in 2002. He is an IEEE Senior Member, and was nominated for the Young Scientist Award at the national level from the Singapore National Academy of Sciences in 2017.
|Date||November 28, 2018 (Wed) 14:00 - 15:00|