Search

Varun Praveen

from Saint Louis, MO
Get Report
Also known as:
Praveen Varun
Connected to:
Kesavan N Praveen, 52Krithika V Praveen, 51Chandra Pravein, 85Tara R Praven, 52Ann M Pravia, 64Sandra J Pravica, 68Constance L Pravikoff, 77Kumar V Pravir, 70Jessica M Pravlik, 44Khemphik K Pravong, 52

Varun Praveen Phones & Addresses

  • Saint Louis, MO
  • San Jose, CA
  • Cupertino, CA
  • Santa Clara, CA
  • Clemson, SC

Work

Company: Ge energy Sep 2010 Position: Project application engineer, quest global services, consultant

Education

School / High School: Clemson University- Clemson, SC Aug 2009 Specialities: Masters of Science in Thermodynamics and Fluid Mechanics

Resumes

Resumes

Varun Praveen Photo 1

Varun Praveen Clifton Park, NY

View page
Work:
GE Energy

Sep 2010 to 2000
Project Application Engineer, QuEST Global Services, Consultant
GE Energy
Atlanta, GA
Oct 2009 to Sep 2010
Technical Analyst, Adecco Technical Services, Consultant
Mechanical Engineering, Clemson University

Aug 2007 to Aug 2009
Graduate Research Assistant
S CADD CENTRE (P) LIMITED

Nov 2006 to Apr 2007
Engineer
Education:
Clemson University
Clemson, SC
Aug 2009
Masters of Science in Thermodynamics and Fluid Mechanics
Jawaharlal Nehru Technological University
May 2006
Bachelor of Science in Mechanical Engineering

Publications

Us Patents

Transfer Learning For Neural Networks

View page
US Patent:
20210089921, Mar 25, 2021
Filed:
Sep 23, 2020
Appl. No.:
17/029725
Inventors:
- Santa Clara CA, US
Varun Praveen - Cupertino CA, US
FNU Ratnesh Kumar - Campbell CA, US
Partha Sriram - Los Altos Hills CA, US
International Classification:
G06N 3/08
G06N 5/04
Abstract:
Transfer learning can be used to enable a user to obtain a machine learning model that is fully trained for an intended inferencing task without having to train the model from scratch. A pre-trained model can be obtained that is relevant for that inferencing task. Additional training data, as may correspond to at least one additional class of data, can be used to further train this model. This model can then be pruned and retrained in order to obtain a smaller model that retains high accuracy for the intended inferencing task.
Control profile
Varun Praveen from Saint Louis, MO Get Report