Patents by Inventor Vaibhav Nagar

Vaibhav Nagar 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).

  • Predictive modeling with entity representations computed from neural network models simultaneously trained on multiple tasks
    Patent number: 11521221
    Abstract: This disclosure involves predictive modeling with entity representations computed from neural network models simultaneously trained on multiple tasks. For example, a method includes a processing device performing operations including accessing input data for an entity and transforming the input data into a dense vector entity representation representing the entity. Transforming the input data includes applying, to the input data, a neural network including simultaneously trained propensity models. Each propensity model predicts a different task based on the input data. Transforming the input data also includes extracting the dense vector entity representation from a common layer of the neural network to which the propensity models are connected.
    Type: Grant
    Filed: March 1, 2018
    Date of Patent: December 6, 2022
    Assignee: ADOBE INC.
    Inventors: Shiv Kumar Saini, Vishwa Vinay, Vaibhav Nagar, Aishwarya Mittal
  • Predictive Modeling with Entity Representations Computed from Neural Network Models Simultaneously Trained on Multiple Tasks
    Publication number: 20190272553
    Abstract: This disclosure involves predictive modeling with entity representations computed from neural network models simultaneously trained on multiple tasks. For example, a method includes a processing device performing operations including accessing input data for an entity and transforming the input data into a dense vector entity representation representing the entity. Transforming the input data includes applying, to the input data, a neural network including simultaneously trained propensity models. Each propensity model predicts a different task based on the input data. Transforming the input data also includes extracting the dense vector entity representation from a common layer of the neural network to which the propensity models are connected.
    Type: Application
    Filed: March 1, 2018
    Publication date: September 5, 2019
    Inventors: Shiv Kumar Saini, Vishwa Vinay, Vaibhav Nagar, Aishwarya Mittal