Patents by Inventor Mahesh Krishnan

Mahesh Krishnan 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: 11983625
    Abstract: Techniques are disclosed for using neural network architectures to estimate predictive uncertainty measures, which quantify how much trust should be placed in the deep neural network (DNN) results. The techniques include measuring reliable uncertainty scores for a neural network, which are widely used in perception and decision-making tasks in automated driving. The uncertainty measurements are made with respect to both model uncertainty and data uncertainty, and may implement Bayesian neural networks or other types of neural networks.
    Type: Grant
    Filed: June 24, 2020
    Date of Patent: May 14, 2024
    Assignee: Intel Corporation
    Inventors: Nilesh Ahuja, Ignacio J. Alvarez, Ranganath Krishnan, Ibrahima J. Ndiour, Mahesh Subedar, Omesh Tickoo
  • Publication number: 20200019995
    Abstract: The present invention uses micro and nano segmentation to create targeted digital content, in the form of segment specific static ads, pictures, carousel, mobile new feeds, video, canvas and other ad types. For example, if the motivation for a health change in an individual is for the sake of their family, specific images or video from social media may be effective in tying the rationale for the change to the messaging. This content can then be delivered is static ads, in carousels or other media options. The content is targeted to a specific user using conventional and unconventional social media targeting systems to assist with the creation of custom campaign delivered over social media for the purposes of influencing positive health behavior.
    Type: Application
    Filed: July 11, 2018
    Publication date: January 16, 2020
    Inventors: Mahesh Krishnan, Akshay Krishnan, Anjali Krishnan
  • Patent number: 7857860
    Abstract: Bone void filler pieces that are conducive to packing or nesting when a plurality of pieces are located in a cavity in random orientation. The bone void filler of the present invention includes a higher bulk packing density and a porosity of less than 80% to provide a better match native bone ingrowth rate. Further, the bone void filler includes a bi-modal pore distribution with a high frequency of smaller pores to enhance the density characteristic of the bone void filler pieces. A method of manufacturing the bone void filler pieces includes a precursor powder composition suitable to form a ceramic matrix; the preform is converted by chemical reaction to a final composition. The preform further includes the use of a porogen that decomposes to gaseous decomposition products upon heating.
    Type: Grant
    Filed: April 30, 2004
    Date of Patent: December 28, 2010
    Assignee: Therics, LLC
    Inventors: Sunil Saini, Jonathan McGlohorn, Qing Liu, Mahesh Krishnan, Jaedeok Yoo, Thomas George West
  • Publication number: 20050027366
    Abstract: Bone void filler pieces that are conducive to packing or nesting when a plurality of pieces are located in a cavity in random orientation. The bone void filler of the present invention includes a higher bulk packing density and a porosity of less than 80% to provide a better match native bone ingrowth rate. Further, the bone void filler includes a bi-modal pore distribution with a high frequency of smaller pores to enhance the density characteristic of the bone void filler pieces. A method of manufacturing the bone void filler pieces includes a precursor powder composition suitable to form a ceramic matrix; the preform is converted by chemical reaction to a final composition. The preform further includes the use of a porogen that decomposes to gaseous decomposition products upon heating.
    Type: Application
    Filed: April 30, 2004
    Publication date: February 3, 2005
    Applicant: Therics, Inc.
    Inventors: Sunil Saini, Jonathan McGlohorn, Qing Liu, Mahesh Krishnan, Jaedeok Yoo, Thomas West