Search

Anshul Kundaje Phones & Addresses

  • Palo Alto, CA
  • San Jose, CA
  • Mountain View, CA
  • Cambridge, MA
  • New York, NY
  • Fremont, CA
  • 100 N Whisman Rd APT 1014, Mountain View, CA 94043

Resumes

Resumes

Anshul Kundaje Photo 1

Assistant Professor

View page
Location:
Stanford, CA
Industry:
Research
Work:
Stanford University
Assistant Professor

Massachusetts Institute of Technology (Mit) Feb 2012 - Aug 2013
Research Scientist

Stanford University Aug 2008 - Feb 2012
Postdoctoral Associate

Columbia University In the City of New York Jun 2010 - Nov 2010
Research Assistant

Columbia University In the City of New York Sep 2003 - Jul 2008
Phd Student
Education:
Columbia University In the City of New York 2003 - 2008
Doctorates, Doctor of Philosophy, Computer Science
Columbia University In the City of New York 2001 - 2002
Master of Science, Masters, Electrical Engineering, Biology
University of Mumbai 1997 - 2001
Bachelor of Engineering, Bachelors, Electrical Engineering
Skills:
Bioinformatics
Computational Biology
Machine Learning
Genetics
Genomics
Systems Biology
Computer Science
Statistics
Matlab
Functional Genomics
Data Mining
Sequencing
Artificial Intelligence
Programming
Dna Sequencing
Distributed Systems
Languages:
Hindi
Marathi
Konkani
Anshul Kundaje Photo 2

Anshul Kundaje

View page
Location:
Cambridge, Massachusetts
Industry:
Research
Skills:
Matlab
Machine Learning
Computational Biology
Bioinformatics
Computer Science
Languages:
Hindi
Marathi
Konkani

Publications

Us Patents

Systems And Methods For Holistic Extraction Of Features From Neural Networks

View page
US Patent:
20170249547, Aug 31, 2017
Filed:
Feb 27, 2017
Appl. No.:
15/444258
Inventors:
- Stanford CA, US
Peyton Greis Greenside - Stanford CA, US
Anshul Kundaje - Palo Alto CA, US
Assignee:
The Board of Trustees of the Leland Stanford Junior University - Stanford CA
International Classification:
G06N 3/04
G06N 3/08
Abstract:
Systems and methods in accordance with embodiments of the invention enable identifying informative features within input data using a neural network data structure. One embodiment includes a data structure describing a neural network that comprises a plurality of neurons; wherein the processor is configured by the feature application to: determine contributions of individual neurons to activation of a target neuron by comparing activations of a set of neurons to their reference values, where the contributions are computed by dynamically backpropagating an importance signal through the data structure describing the neural network; extracting aggregated features detected by the target neuron by: segmenting the determined contributions; clustering into clusters of similar segments; aggregating data to identify aggregated features of input data that contribute to the activation of the target neuron; and displaying aggregated features of input data to highlight important features.
Anshul B Kundaje from Palo Alto, CA, age ~44 Get Report