Search

Animesh Garg

from Redmond, WA
Age ~36
Get Report
Connected to:
Ajay Garg, 53Aseem Garg, 37Ashwani K Garg, 48Bimlesh G Garg, 75Dhruv Garg, 33Gaurav A Garg, 47Gobind L Garg, 78Hari P Garg, 85Indu J Garg, 64Kamla K Garg, 74

Animesh Garg Phones & Addresses

  • Redmond, WA
  • Berkeley, CA
  • San Jose, CA
  • Fremont, CA
  • Menlo Park, CA
  • Atlanta, GA

Resumes

Resumes

Animesh Garg Photo 1

Assistant Professor

View page
Location:
Berkeley, CA
Industry:
Higher Education
Work:
UC Berkeley - San Francisco Bay Area since Aug 2011
PhD Student
UC Berkeley - Berkeley, CA since Aug 2012
Graduate Student Instructor
Education:
University of California, Berkeley 2011 - 2016
University of California, Berkeley 2011 - 2013
Georgia Institute of Technology 2010 - 2011
Netaji Subhas Institute of Technology 2006 - 2010
Delhi University 2006 - 2010
Skills:
Matlab
Machine Learning
Robotics
Computer Vision
Artificial Intelligence
C++
Data Analysis
Operations Research
Optimization
Python
Mathematical Modeling
Statistics
Statistical Modeling
Control Systems Design
Cplex
Computer Science
Autocad
Reinforcement Learning
Deep Reinforcement Learning
Applied Mathematics
Stochastic Processes
Tensorflow
Pytorch
Ros
Probability
Mechatronics
Languages:
English
Hindi
Animesh Garg Photo 2

Animesh Garg

View page

Publications

Us Patents

Disentanglement Of Image Attributes Using A Neural Network

View page
US Patent:
20220180528, Jun 9, 2022
Filed:
Feb 23, 2022
Appl. No.:
17/678666
Inventors:
- Santa Clara CA, US
Kevin Jonathan Shih - Santa Clara CA, US
Animesh Garg - Berkeley CA, US
Robert Thomas Pottorff - Santa Clara CA, US
Andrew Tao - Los Altos CA, US
Bryan Christopher Catanzaro - Los Altos Hills CA, US
International Classification:
G06T 7/194
G06N 20/00
G06N 5/04
G06T 7/70
G06N 3/08
G06V 20/20
Abstract:
Apparatuses, systems, and techniques to perform unsupervised keypoint or landmark learning using one or more neural networks. In at least one embodiment, one or more neural networks use pose and appearance information to construct a foreground and a background, which are then used to reconstruct an input image and determine loss values to train the one or more neural networks.

Guided Uncertainty-Aware Policy Optimization: Combining Model-Free And Model-Based Strategies For Sample-Efficient Learning

View page
US Patent:
20210146531, May 20, 2021
Filed:
Feb 3, 2020
Appl. No.:
16/780465
Inventors:
- Santa Clara CA, US
Dieter Fox - Seattle WA, US
Michelle Lee - Seattle WA, US
Carlos Florensa - Seattle WA, US
Nathan Donald Ratliff - Seattle WA, US
Animesh Garg - Berkeley CA, US
Fabio Tozeto Ramos - Seattle WA, US
International Classification:
B25J 9/16
G05B 13/02
G06N 3/08
G05B 13/04
G06N 5/04
G06N 20/00
Abstract:
A robot is controlled using a combination of model-based and model-free control methods. In some examples, the model-based method uses a physical model of the environment around the robot to guide the robot. The physical model is oriented using a perception system such as a camera. Characteristics of the perception system may be are used to determine an uncertainty for the model. Based at least in part on this uncertainty, the system transitions from the model-based method to a model-free method where, in some embodiments, information provided directly from the perception system is used to direct the robot without reliance on the physical model.

Imitation Learning System

View page
US Patent:
20210081752, Mar 18, 2021
Filed:
Jul 16, 2020
Appl. No.:
16/931211
Inventors:
- Santa Clara CA, US
De-An Huang - Cupertino CA, US
Christopher Jason Paxton - Pittsburgh PA, US
Animesh Garg - Berkeley CA, US
Dieter Fox - Seattle WA, US
International Classification:
G06N 3/00
G06N 20/00
Abstract:
Apparatuses, systems, and techniques to identify a goal of a demonstration. In at least one embodiment, video data of a demonstration is analyzed to identify a goal. Object trajectories identified in the video data are analyzed with respect to a task predicate satisfied by a respective object trajectory, and with respect to motion predicate. Analysis of the trajectory with respect to the motion predicate is used to assess intentionality of a trajectory with respect to the goal.

Video Prediction Using One Or More Neural Networks

View page
US Patent:
20210064925, Mar 4, 2021
Filed:
Sep 3, 2019
Appl. No.:
16/558620
Inventors:
- Santa Clara CA, US
Aysegul Dundar - Santa Clara CA, US
Animesh Garg - Fremont CA, US
Robert Pottorff - Santa Clara CA, US
Andrew Tao - Los Altos CA, US
Bryan Catanzaro - Sunnyvale CA, US
International Classification:
G06K 9/62
G06N 3/04
G06N 3/08
Abstract:
Apparatuses, systems, and techniques to enhance video are disclosed. In at least one embodiment, one or more neural networks are used to create, from a first video, a second video having one or more additional video frames.

Bayesian Optimization Of Sparsity Ratios In Model Compression

View page
US Patent:
20210065052, Mar 4, 2021
Filed:
Feb 7, 2020
Appl. No.:
16/785044
Inventors:
- Santa Clara CA, US
Vinu JOSEPH - Salt Lake City UT, US
Animesh GARG - Berkeley CA, US
Michael GARLAND - Lake Elmo MN, US
International Classification:
G06N 20/00
G06N 7/00
Abstract:
One embodiment of a method includes determining, by a Bayesian optimizer, a first sparsity ratio associated with a limit on an accuracy loss caused by compressing the machine learning model. The method further includes selecting, by the Bayesian optimizer, a second sparsity ratio that optimizes a predefined objective function for the machine learning model within a search space bounded by the first sparsity ratio. The method further includes generating a compressed version of the machine learning model having the second sparsity ratio.

Precision Injector/Extractor For Robot-Assisted Minimally-Invasive Surgery

View page
US Patent:
20180177558, Jun 28, 2018
Filed:
Jun 23, 2016
Appl. No.:
15/738482
Inventors:
- Oakland CA, US
Animesh Garg - Berkeley CA, US
Sachin Patil - Burlingame CA, US
Susan M. L. Lim - Sinagpore, SG
Ken Goldberg - Mill Valley CA, US
Assignee:
The Regents of the University of California - Oakland CA
International Classification:
A61B 34/35
A61B 10/02
A61M 5/20
A61B 34/32
A61B 34/00
B25J 9/16
Abstract:
According to some embodiments of the invention, a surgical robot includes a robot arm having an end effector, the end effector comprising a needle assembly. The surgical robot further includes a robot control system operatively connected to the robot arm, and an end effector control system operatively connected to the end effector. The robot control system provides control signals for operation of the robot arm to move the end effector to selected positions relative to a subject. The end effector control system is configured to provide signals for operation of the end effector to at least one of inject material through the needle assembly to a selected location within the subject's body or extract material through the needle assembly from the selected location within the subject's body.

Patient-Specific Temporary Implants For Accurately Guiding Local Means Of Tumor Control Along Patient-Specific Internal Channels To Treat Cancer

View page
US Patent:
20160271379, Sep 22, 2016
Filed:
Jul 28, 2014
Appl. No.:
14/907679
Inventors:
- Oakland CA, US
Ken GOLDBERG - Mill Valley CA, US
J. Adam M. CHNHA - San Bruno CA, US
Animesh GARG - Berkeley CA, US
Sachin PATEL - Berkeley CA, US
Pieter ABBEEL - Berkeley CA, US
Timmy SIAUW - Berkeley CA, US
International Classification:
A61M 31/00
A61B 8/08
A61B 6/03
A61N 5/06
A61N 5/10
Abstract:
The present invention offers an alternative for cancer treatment where radiation, thermotherapy, or another therapeutic modality must be delivered to an internal cavity of a subject, for example to treat mouth, anal, cervical, and vaginal cancers. The invention is a new approach that builds on recent results in 3D printing and steerable needle motion planning to create customized implants containing customized curvature-constrained internal channels that fit securely, minimize air gaps, and precisely guide treatment sources through internal printed channels to accurately reach tumors and minimize damage to healthy tissue.
Control profile
Animesh Garg from Redmond, WA, age ~36 Get Report