About me
I'm an engineering leader, researcher, and educator working on the potential of machine learning, data science, and artificial intelligence to improve people's lives.
I'm currently a Machine Learning Architect at Manifold, where I lead AI development projects for leading companies. My team and I apply machine learning to solve critical business problems for our customers, and deliver production-grade AI solutions.
I'm also involved in a number of teaching and education initiatives. Currently, I'm teaching UC Berkeley's capstone data science course, Data 102 with my colleague Yan Shuo Tan. In the past, I've also taught Berkeley's introductory data science course, Data 8.
You can also find me on github and LinkedIn.
A brief history
Before Manifold, I was Head of Machine Learning at Vidado (formerly known as Captricity), where I led a team of machine learning engineers building algorithms to digitize and make sense of data from paper forms and documents.
I've volunteered with several organizations using education to help bring about positive social change. Most recently, I've worked as a tutor for the Prison University Project, helping to provide a rigorous education to incarcerated people. I've also worked as an instructor for MEET, bringing together Palestinian and Israeli youth through education in computer science and entrepreneurship.
In the not-so-distant past, I completed my PhD in the Medical Vision Group at CSAIL, where I was supervised by Polina Golland. For my PhD, I worked on applications of machine learning and artificial intelligence to problems in medical imaging. I was funded by the NSF Graduate Research Fellowship.
In the more distant past, I was an undergraduate in EECS at UC Berkeley. While I was there I worked with Stan Klein's Visual Processing Lab on signal processing in vision science, and with Dan Garcia and Brian Harvey on a (now-defunct) curriculum development project involving parallelism in introductory computer science courses.
Publications
-
Adrian Dalca, Ramesh Sridharan, Natalia Rost, and Polina Golland.
"tipiX: Rapid Visualization of Large Image Collections."
In MICCAI Interactive Medical Image Computing (IMIC), 2014.
Best paper award for impact and usability.
[Paper] -
Ramesh Sridharan, Adrian Dalca, and Polina Golland.
"An Interactive Visualization Tool for Nipype Medical
Image Computing Pipelines." In MICCAI Interactive Medical Image Computing (IMIC), 2014.
[Paper] [Live demo] -
Adrian Dalca, Ramesh Sridharan,
Lisa Cloonan, Kaitlin Fitzpatrick, Allison Kanakis, Karen Furie,
Ona Wu, Jonathan Rosand, Natalia Rost, and Polina Golland.
"Segmentation of Cerebrovascular Pathologies in Stroke Patients with Spatial and Shape Priors."
In Proceedings MICCAI: International Conference on Medical
Image Computing and Computer Assisted Intervention (MICCAI)
2014.
[Paper] -
Sophie Chou*, William Li*, and Ramesh Sridharan*.
"Democratizing Data Science."
KDD@Bloomberg, 2014.
[Paper] -
Ramesh Sridharan*, Adrian Dalca*,
Kaitlin Fitzpatrick, Lisa Cloonan, Allison Kanakis, Ona Wu,
Karen Furie, Jonathan Rosand, Natalia Rost, and Polina
Golland. "Quantification and
Analysis of Large Multimodal Clinical Image Studies:
Application to Stroke." In Proceedings MICCAI
International Workshop on Multimodal Brain Image Analaysis
(MBIA), 2013.
[Paper] [Poster] -
Danial Lashkari, Ramesh
Sridharan, Ed Vul, Po-Jang Hsieh, Nancy Kanwisher,
and Polina Golland. "Search for
Patterns of Functional Specificity in the Brain: A
Nonparametric Hierarchical Bayesian Model for Group fMRI
Data." NeuroImage, 59(2):1348-1368, 2012.
[Paper] - Ramesh Sridharan. "A Generative Model for Activations in Functional MRI." Master's Thesis, MIT, 2011.
-
Danial Lashkari, Ramesh Sridharan, and Polina Golland.
"Categories and Functional Units: An Infinite Hierarchical
Model for Brain Activations." Accepted in Advances in Neural
Information Processing Systems (NIPS), 2010.
[Paper] [Poster] -
Danial Lashkari, Ramesh Sridharan, Ed Vul, Po-Jang
Hsieh, Nancy G. Kanwisher, and Polina Golland.
"Nonparametric Hierarchical Bayesian Model for Functional
Brain Parcellation." In Proceedings of MMBIA: IEEE
Computer Society Workshop on Mathematical Methods in
Biomedical Image Analysis, 2010.
[Paper] -
Matthew Johnson*, Ramesh Sridharan*,
Robert H. Liao, Alexander Rasmussen, Dan Garcia and Brian K.
Harvey.
"Infusing Parallelism into Introductory Computer Science
Curriculum using MapReduce." UC Berkeley Technical Report
No. UCB/EECS-2008-34, 2008.
[Paper]
* Indicates equal contribution