Current Members

Assistant HES, PhD student CS UNIGE
Jason Ramapuram

Bio

Jason Ramapuram joined the DMML team in 2015. He completed his Masters in Electrical Engineering (with a focus on Signal Processing) in 2011 from the University of California, Riverside. Until joining the DMML team Jason worked as a Software Engineer at Qualcomm Inc and later as a Machine Learning Engineer at Viasat Inc. Jason has also done academic internships at Apple AI Research and Rockwell Collins Advanced Technology Center.

Research

Jason is actively working on Lifelong Learning for Generative Models as well as Variational approaches to allow CNN’s to work over ultra-high dimensional image data (eg: 4k / 8k images).

Publications

2018

Large-scale Nonlinear Variable Selection via Kernel Random Features Journal Article

Gregorová, Magda; Ramapuram, Jason; Kalousis, Alexandros; Marchand-Maillet, Stéphane

CoRR, abs/1804.07169 , 2018.

Links | BibTeX

A New Benchmark and Progress Toward Improved Weakly Supervised Learning Journal Article

Ramapuram, Jason; Webb, Russ

CoRR, abs/1807.00126 , 2018.

Links | BibTeX

2017

Lifelong Generative Modeling Journal Article

Ramapuram, Jason; Gregorova, Magda; Kalousis, Alexandros

CoRR, abs/1705.09847 , 2017.

Links | BibTeX