Patents by Inventor Vashisht Madhavan

Vashisht Madhavan has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Training neural networks using evolution based strategies and novelty search
    Patent number: 11068787
    Abstract: Systems and methods are disclosed herein for selecting a parameter vector from a set of parameter vectors for a neural network and generating a plurality of copies of the parameter vector. The systems and methods generate a plurality of modified parameter vectors by perturbing each copy of the parameter vector with a different perturbation seed, and determine, for each respective modified parameter vector, a respective measure of novelty. The systems and methods determine an optimal new parameter vector based on each respective measure of novelty for each respective one of the plurality of modified parameter vectors, and determine behavior characteristics of the new parameter vector. The systems and methods store the behavior characteristics of the new parameter vector in an archive.
    Type: Grant
    Filed: December 14, 2018
    Date of Patent: July 20, 2021
    Assignee: Uber Technologies, Inc.
    Inventors: Edoardo Conti, Vashisht Madhavan, Jeffrey Michael Clune, Felipe Petroski Such, Joel Anthony Lehman, Kenneth Owen Stanley
  • Scalable parameter encoding of artificial neural networks obtained via an evolutionary process
    Patent number: 10599975
    Abstract: A source system initializes, using an initialization seed, a first parameter vector representing weights of a neural network. The source system determines a second parameter vector by performing a sequence of mutations on the first parameter vector, the mutations each being based on a perturbation seed. The source system generates, and stores to memory, an encoded representation of the second parameter vector that comprises the initialization seed and a sequence of perturbation seeds corresponding to the sequence of mutations. The source system transmits the data structure to a target system, which processes a neural network based on the data structure.
    Type: Grant
    Filed: December 14, 2018
    Date of Patent: March 24, 2020
    Assignee: Uber Technologies, Inc.
    Inventors: Felipe Petroski Such, Jeffrey Michael Clune, Kenneth Owen Stanley, Edoardo Conti, Vashisht Madhavan, Joel Anthony Lehman
  • TRAINING NEURAL NETWORKS USING EVOLUTION BASED STRATEGIES AND NOVELTY SEARCH
    Publication number: 20190188571
    Abstract: Systems and methods are disclosed herein for selecting a parameter vector from a set of parameter vectors for a neural network and generating a plurality of copies of the parameter vector. The systems and methods generate a plurality of modified parameter vectors by perturbing each copy of the parameter vector with a different perturbation seed, and determine, for each respective modified parameter vector, a respective measure of novelty. The systems and methods determine an optimal new parameter vector based on each respective measure of novelty for each respective one of the plurality of modified parameter vectors, and determine behavior characteristics of the new parameter vector. The systems and methods store the behavior characteristics of the new parameter vector in an archive.
    Type: Application
    Filed: December 14, 2018
    Publication date: June 20, 2019
    Inventors: Edoardo Conti, Vashisht Madhavan, Jeffrey Michael Clune, Felipe Petroski Such, Joel Anthony Lehman, Kenneth Owen Stanley
  • SCALABLE PARAMETER ENCODING OF ARTIFICIAL NEURAL NETWORKS OBTAINED VIA AN EVOLUTIONARY PROCESS
    Publication number: 20190188553
    Abstract: A source system initializes, using an initialization seed, a first parameter vector representing weights of a neural network. The source system determines a second parameter vector by performing a sequence of mutations on the first parameter vector, the mutations each being based on a perturbation seed. The source system generates, and stores to memory, an encoded representation of the second parameter vector that comprises the initialization seed and a sequence of perturbation seeds corresponding to the sequence of mutations. The source system transmits the data structure to a target system, which processes a neural network based on the data structure.
    Type: Application
    Filed: December 14, 2018
    Publication date: June 20, 2019
    Inventors: Felipe Petroski Such, Jeffrey Michael Clune, Kenneth Owen Stanley, Edoardo Conti, Vashisht Madhavan, Joel Anthony Lehman