Patents by Inventor Nehal Desai

Nehal Desai 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).

  • Patent number: 11308402
    Abstract: Artificial intelligence (AI) techniques that map disallowed states and enable access to those states under certain conditions through a search algorithm are disclosed. In other words, scenario boundaries may be crossed by jumping from one scenario that is less desirable or even has no solution to another scenario that is more desirable.
    Type: Grant
    Filed: July 2, 2020
    Date of Patent: April 19, 2022
    Assignee: THE AEROSPACE CORPORATION
    Inventors: Terence Yeoh, Nehal Desai
  • Patent number: 10832180
    Abstract: An artificial intelligence (AI) system is disclosed that employs windowed cellular automata to create plausible alternatives. A cellular automata-based technique may be utilized to perform pattern recognition and assess the best path available (i.e., “instant improv”). Alternative sequences (i.e., “pattern improv”) may also be used to determine alternative paths. This instant improv and pattern improv may then be used to create completely new, plausible alternative nodes. The subsequent evaluation of the sentiment further creates new, dynamic capabilities. Through the use of windowed memory learning, recall, and interpolation, new plausible structures are generated that predict dynamic systems.
    Type: Grant
    Filed: October 22, 2018
    Date of Patent: November 10, 2020
    Assignee: The Aerospace Corporation
    Inventors: Terence Yeoh, Nehal Desai
  • Publication number: 20200334549
    Abstract: Artificial intelligence (AI) techniques that map disallowed states and enable access to those states under certain conditions through a search algorithm are disclosed. In other words, scenario boundaries may be crossed by jumping from one scenario that is less desirable or even has no solution to another scenario that is more desirable.
    Type: Application
    Filed: July 2, 2020
    Publication date: October 22, 2020
    Applicant: The Aerospace Corporation
    Inventors: Terence Yeoh, Nehal Desai
  • Patent number: 10762431
    Abstract: Artificial intelligence (AI) techniques that map disallowed states and enable access to those states under certain conditions through a search algorithm are disclosed. In other words, scenario boundaries may be crossed by jumping from one scenario that is less desirable or even has no solution to another scenario that is more desirable.
    Type: Grant
    Filed: May 1, 2018
    Date of Patent: September 1, 2020
    Assignee: The Aerospace Corporation
    Inventors: Terence Yeoh, Nehal Desai
  • Patent number: 10740646
    Abstract: An architecture and process are provided that encodes information into a cellular automata memory structure such that it can be recalled utilizing unique memory anchors (engrams) in a manner that both identifies and relates each piece of information relative to other data points. The automata may be individually programmable with a limited, local ruleset that activates other cellular automata based on prior patterns that were fed into the array. Deep Learning Neural Network (DLNN) systems may be probed to understand what discriminators are being used to classify the data, which is not possible with conventional DLNN techniques.
    Type: Grant
    Filed: October 30, 2017
    Date of Patent: August 11, 2020
    Assignee: The Aerospace Corporation
    Inventors: Terence S. Yeoh, Nehal Desai
  • Publication number: 20190130287
    Abstract: Artificial intelligence (AI) techniques that map disallowed states and enable access to those states under certain conditions through a search algorithm are disclosed. In other words, scenario boundaries may be crossed by jumping from one scenario that is less desirable or even has no solution to another scenario that is more desirable.
    Type: Application
    Filed: May 1, 2018
    Publication date: May 2, 2019
    Applicant: The Aerospace Corporation
    Inventors: Terence Yeoh, Nehal Desai
  • Publication number: 20190130321
    Abstract: An artificial intelligence (AI) system is disclosed that employs windowed cellular automata to create plausible alternatives. A cellular automata-based technique may be utilized to perform pattern recognition and assess the best path available (i.e., “instant improv”). Alternative sequences (i.e., “pattern improv”) may also be used to determine alternative paths. This instant improv and pattern improv may then be used to create completely new, plausible alternative nodes. The subsequent evaluation of the sentiment further creates new, dynamic capabilities. Through the use of windowed memory learning, recall, and interpolation, new plausible structures are generated that predict dynamic systems.
    Type: Application
    Filed: October 22, 2018
    Publication date: May 2, 2019
    Applicant: The Aerospace Corporation
    Inventors: Terence Yeoh, Nehal Desai
  • Publication number: 20190130207
    Abstract: An architecture and process are provided that encodes information into a cellular automata memory structure such that it can be recalled utilizing unique memory anchors (engrams) in a manner that both identifies and relates each piece of information relative to other data points. The automata may be individually programmable with a limited, local ruleset that activates other cellular automata based on prior patterns that were fed into the array. Deep Learning Neural Network (DLNN) systems may be probed to understand what discriminators are being used to classify the data, which is not possible with conventional DLNN techniques.
    Type: Application
    Filed: October 30, 2017
    Publication date: May 2, 2019
    Applicant: The Aerospace Corporation
    Inventors: Terence Yeoh, Nehal Desai
  • Publication number: 20060143710
    Abstract: Provided are a techniques for monitoring communication packets. A communication packet is received. A communication packet signature of the communication packet is determined. The communication packet signature is compared to one or more site-specific application signatures. In response to determining that the communication packet signature matches at least of the one or more site-specific application signatures, it is determined that the communication packet is to be trusted.
    Type: Application
    Filed: December 29, 2004
    Publication date: June 29, 2006
    Inventors: Nehal Desai, Patrick Chauvin, Jac Noel