Patents by Inventor Philip M. Long
Philip M. Long 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: 11409991Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a convolutional neural network using a regularization scheme. One of the methods includes repeatedly performing the following operations: obtaining a kernel of a particular convolutional layer; applying a Fourier transform to the kernel; generating a decomposition using singular-value decomposition (SVD); generating a regularized diagonal matrix; generating a recomposition; applying an inverse Fourier transform to the recomposition; and training the convolutional neural network on training inputs.Type: GrantFiled: May 24, 2019Date of Patent: August 9, 2022Assignee: Google LLCInventors: Vineet Gupta, Philip M. Long, Hanie Sedghi
-
Patent number: 11403532Abstract: A method for finding a solution to a problem is provided. The method includes storing candidate individuals in a candidate pool and evolving the candidate individuals by performing steps including (i) testing each of the candidate individuals to obtain test results, (ii) assigning a performance measure to the tested candidate individuals, (iii) discarding candidate individuals from the candidate pool in dependence upon their assigned performance measure, and (iv) adding, to the candidate pool, a new candidate individual procreated from candidate individuals remaining in the candidate pool.Type: GrantFiled: March 2, 2018Date of Patent: August 2, 2022Assignee: Cognizant Technology Solutions U.S. CorporationInventors: Risto Miikkulainen, Hormoz Shahrzad, Nigel Duffy, Philip M. Long
-
Patent number: 10909459Abstract: The technology disclosed introduces a concept of training a neural network to create an embedding space. The neural network is trained by providing a set of K+2 training documents, each training document being represented by a training vector x, the set including a target document represented by a vector xt, a favored document represented by a vector xs, and K>1 unfavored documents represented by vectors xiu, each of the vectors including input vector elements, passing the vector representing each document set through the neural network to derive an output vectors yt, ys and yiu, each output vector including output vector elements, the neural network including adjustable parameters which dictate an amount of influence imposed on each input vector element to derive each output vector element, adjusting the parameters of the neural network to reduce a loss, which is an average over all of the output vectors yiu of [D(yt,ys)?D(yt, yiu)].Type: GrantFiled: June 9, 2017Date of Patent: February 2, 2021Assignee: Cognizant Technology Solutions U.S. CorporationInventors: Petr Tsatsin, Philip M. Long, Diego Guy M. Legrand, Nigel Duffy
-
Publication number: 20200372300Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a convolutional neural network using a regularization scheme. One of the methods includes repeatedly performing the following operations: obtaining a kernel of a particular convolutional layer; applying a Fourier transform to the kernel; generating a decomposition using singular-value decomposition (SVD); generating a regularized diagonal matrix; generating a recomposition; applying an inverse Fourier transform to the recomposition; and training the convolutional neural network on training inputs.Type: ApplicationFiled: May 24, 2019Publication date: November 26, 2020Inventors: Vineet Gupta, Philip M. Long, Hanie Sedghi
-
Patent number: 10606883Abstract: Roughly described, a system for user identification of a desired document. A database identifies a catalog of documents in an embedding space, in which the distance between documents corresponds to a measure of their dissimilarity. The system presents an initial collection of the documents toward the user from an initial candidate space which is part of the embedding space, then in response to iterative user input, refines the candidate space and subsequent collections of documents presented toward the user. The initial collection is determined using a weighted cost-based iterative addition to the initial collection of documents from the initial candidate space, trading off between two sub-objectives of representativeness and diversity.Type: GrantFiled: October 17, 2016Date of Patent: March 31, 2020Assignee: EVOLV TECHNOLOGY SOLUTIONS, INC.Inventors: Diego Legrand, Philip M. Long, Nigel Duffy
-
Patent number: 10102277Abstract: A method for identifying a desired document is provided to include calculating a Prior probability score for each document of a candidate list including a portion of documents of an embedding space, the Prior probability score indicating a preliminary probability, for each document of the candidate list, that the document is the desired document, and identifying an initial (i=0) collection of N0>1 candidate documents from the candidate list in dependence on the calculated Prior probability scores, the initial collection of candidate documents having fewer documents than the candidate list. The method further includes, for each i'th iteration in a plurality of iterations, beginning with a first iteration (i=1) and in response to user selection of an i'th selected document from the (i?1)'th collection of candidate documents, identifying an i'th collection of Ni>1 candidate documents from the candidate list in dependence on Posterior probability scores.Type: GrantFiled: December 9, 2016Date of Patent: October 16, 2018Assignee: SENTIENT TECHNOLOGIES (BARBADOS) LIMITEDInventors: Diego Guy M. Legrand, Philip M. Long, Nigel Duffy, Olivier Francon
-
Publication number: 20180253649Abstract: A method for finding a solution to a problem is provided. The method includes storing candidate individuals in a candidate pool and evolving the candidate individuals by performing steps including (i) testing each of the candidate individuals to obtain test results, (ii) assigning a performance measure to the tested candidate individuals, (iii) discarding candidate individuals from the candidate pool in dependence upon their assigned performance measure, and (iv) adding, to the candidate pool, a new candidate individual procreated from candidate individuals remaining in the candidate pool.Type: ApplicationFiled: March 2, 2018Publication date: September 6, 2018Applicant: SENTIENT TECHNOLOGIES (BARBADOS) LIMITEDInventors: Risto MIIKKULAINEN, Hormoz SHAHRZAD, Nigel DUFFY, Philip M. LONG
-
Publication number: 20170357896Abstract: The technology disclosed introduces a concept of training a neural network to create an embedding space. The neural network is trained by providing a set of K+2 training documents, each training document being represented by a training vector x, the set including a target document represented by a vector xt, a favored document represented by a vector xs, and K>1 unfavored documents represented by vectors xiu, each of the vectors including input vector elements, passing the vector representing each document set through the neural network to derive an output vectors yt, ys and yiu, each output vector including output vector elements, the neural network including adjustable parameters which dictate an amount of influence imposed on each input vector element to derive each output vector element, adjusting the parameters of the neural network to reduce a loss, which is an average over all of the output vectors yiu of [D(yt,ys)?D(yt,yiu)].Type: ApplicationFiled: June 9, 2017Publication date: December 14, 2017Applicant: Sentient Technologies (Barbados) LimitedInventors: Petr TSATSIN, Philip M. LONG, Diego Guy M. LEGRAND, Nigel DUFFY
-
Publication number: 20170091319Abstract: A method for identifying a desired document is provided to include calculating a Prior probability score for each document of a candidate list including a portion of documents of an embedding space, the Prior probability score indicating a preliminary probability, for each document of the candidate list, that the document is the desired document, and identifying an initial (i=0) collection of N0>1 candidate documents from the candidate list in dependence on the calculated Prior probability scores, the initial collection of candidate documents having fewer documents than the candidate list. The method further includes, for each i'th iteration in a plurality of iterations, beginning with a first iteration (i=1) and in response to user selection of an i'th selected document from the (i?1)'th collection of candidate documents, identifying an i'th collection of Ni>1 candidate documents from the candidate list in dependence on Posterior probability scores.Type: ApplicationFiled: December 9, 2016Publication date: March 30, 2017Applicant: SENTIENT TECHNOLOGIES (BARBADOS) LIMITEDInventors: Diego Guy M. Legrand, Philip M. Long, Nigel Duffy, Olivier Francon
-
Publication number: 20170031904Abstract: Roughly described, a system for user identification of a desired document. A database identifies a catalog of documents in an embedding space, in which the distance between documents corresponds to a measure of their dissimilarity. The system presents an initial collection of the documents toward the user from an initial candidate space which is part of the embedding space, then in response to iterative user input, refines the candidate space and subsequent collections of documents presented toward the user. The initial collection is determined using a weighted cost-based iterative addition to the initial collection of documents from the initial candidate space, trading off between two sub-objectives of representativeness and diversity.Type: ApplicationFiled: October 17, 2016Publication date: February 2, 2017Applicant: SENTIENT TECHNOLOGIES (BARBADOS) LIMITEDInventors: Diego Legrand, Philip M. Long, Nigel Duffy
-
Patent number: 8036996Abstract: Boosting algorithms are provided for accelerated machine learning in the presence of misclassification noise. In an exemplary embodiment, a machine learning method having multiple learning stages is provided. Each learning stage may include partitioning examples into bins, choosing a base classifier for each bin, and assigning an example to a bin by counting the number of positive predictions previously made by the base classifier associated with the bin.Type: GrantFiled: March 10, 2008Date of Patent: October 11, 2011Assignee: The Trustees of Columbia University in the City of New YorkInventors: Philip M. Long, Rocco A. Servedio, Roger N. Anderson, Albert Boulanger
-
Publication number: 20080270329Abstract: Boosting algorithms are provided for accelerated machine learning in the presence of misclassification noise. In an exemplary embodiment, a machine learning method having multiple learning stages is provided. Each learning stage may include partitioning examples into bins, choosing a base classifier for each bin, and assigning an example to a bin by counting the number of positive predictions previously made by the base classifier associated with the bin.Type: ApplicationFiled: March 10, 2008Publication date: October 30, 2008Inventors: Philip M. Long, Rocco A. Servedio, Roger N. Anderson, Albert Boulanger