Search

Apoorv Khandelwal Phones & Addresses

  • Emeryville, CA
  • Dublin, CA
  • Santa Clara, CA
  • Newport Beach, CA
  • Seattle, WA
  • Burtonsville, MD
  • Akron, OH

Work

Company: Carnegie mellon university Aug 2012 to May 2013 Address: Greater Pittsburgh Area Position: Teaching assistant

Education

Degree: Master of Science School / High School: Carnegie Mellon University 2012 to 2013 Specialities: Electrical and Computer Engineering

Skills

Machine Learning • Software Engineering • Java • Programming • Probability • Algorithms • Computer Science • Factorization Machine • Python • Matlab • C • Software Development • Unix • Mapreduce • Stochastic Processes • Algorithm Design • Linux • Shell Scripting • Hive • Mongodb • Intellij Idea • Apache Spark • Scala • Apache Pig

Languages

English • Hindi • French

Interests

Problem Solving • Machine Learning • Probability • Deep Learning • Tennis • Graph Theory • No Limit Texas Hold'em

Industries

Internet

Resumes

Resumes

Apoorv Khandelwal Photo 1

Co-Founder And Chief Technology Officer

View page
Location:
6363 Christie Ave, Emeryville, CA 94608
Industry:
Internet
Work:
Carnegie Mellon University - Greater Pittsburgh Area Aug 2012 - May 2013
Teaching Assistant

Carnegie Mellon University - Greater Pittsburgh Area Aug 2009 - May 2013
Coordinating Peer Tutor

Carnegie Mellon University - Greater Pittsburgh Area May 2012 - Aug 2012
Student Researcher

Macquarie Group - Greater New York City Area Jun 2011 - Aug 2011
Software Developer Intern

Sandia National Laboratories - Albuquerque, New Mexico Area Jun 2010 - Aug 2010
Electrical Engineer Intern
Education:
Carnegie Mellon University 2012 - 2013
Master of Science, Electrical and Computer Engineering
Carnegie Mellon University 2008 - 2012
Bachelor of Science, Electrical and Computer Engineering
Skills:
Machine Learning
Software Engineering
Java
Programming
Probability
Algorithms
Computer Science
Factorization Machine
Python
Matlab
C
Software Development
Unix
Mapreduce
Stochastic Processes
Algorithm Design
Linux
Shell Scripting
Hive
Mongodb
Intellij Idea
Apache Spark
Scala
Apache Pig
Interests:
Problem Solving
Machine Learning
Probability
Deep Learning
Tennis
Graph Theory
No Limit Texas Hold'em
Languages:
English
Hindi
French

Publications

Us Patents

Negative Sampling

View page
US Patent:
20190163668, May 30, 2019
Filed:
Nov 30, 2017
Appl. No.:
15/827329
Inventors:
- Redmond WA, US
Benjamin John McCann - Mountain view CA, US
David DiCato - San Francisco CA, US
Jerry Lin - San Jose CA, US
Skylar Payne - Sunnyvale CA, US
Apoorv Khandelwal - Santa Clara CA, US
Nadeem Anjum - Santa Clara CA, US
International Classification:
G06F 15/18
G06F 17/16
G06Q 10/10
Abstract:
Systems and methods for predicting feature values in a matrix are disclosed. In example embodiments, a server accesses a matrix, the matrix having multiple dimensions, one dimension of the matrix representing features, and one dimension of the matrix representing entities. The server separates the matrix into multiple submatrices along a first dimension, each submatrix including all cells in the matrix for a set of values in the first dimension. The server provides the multiple submatrices to multiple machines. The server computes, using each machine, a correlation between values in at least one second dimension of the matrix and a value for a preselected feature in the matrix, the correlation being used to predict the value for the preselected feature based on other values along the at least one second dimension. The server provides an output representing the computed correlation.

Machine Learning To Predict Numerical Outcomes In A Matrix-Defined Problem Space

View page
US Patent:
20190163718, May 30, 2019
Filed:
Nov 30, 2017
Appl. No.:
15/827350
Inventors:
- Redmond WA, US
Benjamin John McCann - Mountain View CA, US
David DiCato - San Francisco CA, US
Jerry Lin - San Jose CA, US
Skylar Payne - Sunnyvale CA, US
Apoorv Khandelwal - Santa Clara CA, US
Nadeem Anjum - Santa Clara CA, US
International Classification:
G06F 17/16
G06F 17/15
G06F 17/17
G06F 17/18
Abstract:
Systems and methods for predicting feature values in a matrix are disclosed. In example embodiments, a server accesses a matrix, the matrix having multiple dimensions, one dimension of the matrix representing features, and one dimension of the matrix representing entities. The server separates the matrix into multiple submatrices along a first dimension, each submatrix including all cells in the matrix for a set of values in the first dimension. The server provides the multiple submatrices to multiple machines. The server computes, using each machine, a correlation between values in at least one second dimension of the matrix and a value for a preselected feature in the matrix, the correlation being used to predict the value for the preselected feature based on other values along the at least one second dimension. The server provides an output representing the computed correlation.

Predicting Feature Values In A Matrix

View page
US Patent:
20190164096, May 30, 2019
Filed:
Nov 30, 2017
Appl. No.:
15/827289
Inventors:
- Redmond WA, US
Benjamin John McCann - Mountain View CA, US
David DiCato - San Francisco CA, US
Jerry Lin - San Jose CA, US
Skylar Payne - Sunnyvale CA, US
Apoorv Khandelwal - Santa Clara CA, US
Nadeem Anjum - Santa Clara CA, US
International Classification:
G06Q 10/06
G06N 5/02
Abstract:
Systems and methods for predicting feature values in a matrix are disclosed. In example embodiments, a server accesses a matrix, the matrix having multiple dimensions, one dimension of the matrix representing features, and one dimension of the matrix representing entities. The server separates the matrix into multiple submatrices along a first dimension, each submatrix including all cells in the matrix for a set of values in the first dimension. The server provides the multiple submatrices to multiple machines. The server computes, using each machine, a correlation between values in at least one second dimension of the matrix and a value for a preselected feature in the matrix, the correlation being used to predict the value for the preselected feature based on other values along the at least one second dimension. The server provides an output representing the computed correlation.

Ranking Job Candidate Search Results

View page
US Patent:
20190164132, May 30, 2019
Filed:
Nov 30, 2017
Appl. No.:
15/827337
Inventors:
- Redmond WA, US
Benjamin John McCann - Mountain View CA, US
David DiCato - San Francisco CA, US
Jerry Lin - San Jose CA, US
Skylar Payne - Sunnyvale CA, US
Apoorv Khandelwal - Santa Clara CA, US
Nadeem Anjum - Santa Clara CA, US
International Classification:
G06Q 10/10
G06Q 10/06
Abstract:
Systems and methods for predicting feature values in a matrix are disclosed. In example embodiments, a server accesses a matrix, the matrix having multiple dimensions, one dimension of the matrix representing features, and one dimension of the matrix representing entities. The server separates the matrix into multiple submatrices along a first dimension, each submatrix including all cells in the matrix for a set of values in the first dimension. The server provides the multiple submatrices to multiple machines. The server computes, using each machine, a correlation between values in at least one second dimension of the matrix and a value for a preselected feature in the matrix, the correlation being used to predict the value for the preselected feature based on other values along the at least one second dimension. The server provides an output representing the computed correlation.
Apoorv Khandelwal from Emeryville, CA, age ~34 Get Report