Tejaswini L Ganapathi from Piedmont, CA, age 40

Tejaswini Ganapathi Phones & Addresses

Piedmont, CA
Berkeley, CA
San Francisco, CA
Redwood City, CA
Austin, TX
Houston, TX

Work

Company:

Intelligent data analysis and exploration lab, ut austin
Jun 2013
Position:

Graduate research assistant

Education

School / High School:

The University of Texas at Austin- Austin, TX
Aug 2010
Specialities:

PhD in Electrical and Computer Engineering

Skills

Machine Learning • Data Mining • Python • C# • C • Unix Shell • SQL • R • SAS

Resumes

Tejaswini Ganapathi Austin, TX

view source

Work:

Intelligent Data Analysis and Exploration Lab, UT Austin

Jun 2013 to 2000
Graduate Research Assistant MD Anderson Cancer Center and UT Austin
Austin, TX
Sep 2010 to Dec 2012
Graduate Research Assistant Quantlab Financial Inc
Houston, TX
May 2012 to Aug 2012
Quantitative Research Intern IBM Life Sciences Discovery Center
Toronto, ON
Feb 2010 to Aug 2010
Research Programmer Sentinelle Medical Inc
Toronto, ON
Aug 2008 to Dec 2009
Software Developer Multimedia Lab, University of Toronto
Toronto, ON
Sep 2006 to Jul 2008
Graduate Research Assistant

Education:

The University of Texas at Austin
Austin, TX
Aug 2010 to 2000
PhD in Electrical and Computer Engineering University of Toronto
Toronto, ON
2006 to 2008
Electrical and Computer Engineering Birla Institute of Technology and Science
Dubai
2002 to 2006
BE in Electrical and Electronics Engineering

Skills:

Machine Learning, Data Mining, Python, C#, C, Unix Shell, SQL, R, SAS

Us Patents

Adaptive Multi-Phase Network Policy Optimization
view source
US Patent:

20180331908, Nov 15, 2018
Filed:

May 12, 2017
Appl. No.:

15/593635
Inventors:

- San Francisco CA, US
Satish Raghunath - Sunnyvale CA, US
Kartikeya Chandrayana - San Francisco CA, US
Tejaswini Ganapathi - San Francisco CA, US
International Classification:

H04L 12/24
H04L 29/06
H04L 29/08
H04L 12/26
Abstract:

An adaptive multi-phase approach to estimating network parameters is presented. By gathering and aggregating raw network traffic data and comparing against default network parameters, a training data set may be generated. A black box optimization may be used in tandem with a supervised learning algorithm to bias towards better choices and eventually pick network parameters which optimize performance. Data delivery strategies are applied to deliver content using the optimized network policies based on the estimated parameters.

Tejaswini L Ganapathi