Patents by Inventor Stephen Gould

Stephen Gould 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: 10534965
    Abstract: Techniques for analyzing stored video upon a request are described. For example, a method of receiving a first application programming interface (API) request to analyze a stored video, the API request to include a location of the stored video and at least one analysis action to perform on the stored video; accessing the location of the stored video to retrieve the stored video; segmenting the accessed video into chunks; processing each chunk with a chunk processor to perform the at least one analysis action, each chunk processor to utilize at least one machine learning model in performing the at least one analysis action; joining the results of the processing of each chunk to generate a final result; storing the final result; and providing the final result to a requestor in response to a second API request is described.
    Type: Grant
    Filed: March 20, 2018
    Date of Patent: January 14, 2020
    Assignee: Amazon Technologies, Inc.
    Inventors: Nitin Singhal, Vivek Bhadauria, Ranju Das, Gaurav D. Ghare, Roman Goldenberg, Stephen Gould, Kuang Han, Jonathan Andrew Hedley, Gowtham Jeyabalan, Vasant Manohar, Andrea Olgiati, Stefano Stefani, Joseph Patrick Tighe, Praveen Kumar Udayakumar, Renjun Zheng
  • Publication number: 20190385292
    Abstract: A method of completing a masked image includes, in part, identifying a multitude of images that are visually similar to the masked image, retrieving a first subset of images from the multitude of images, setting parameters of a neural network to a first set of values in accordance with the data represented by the first retrieved subset, and using the neural network with the first set of parameters to complete the masked image if the neural network having the first set of parameters is determined to meet a threshold value. If the neural network having the first set of parameters is determined not to meet the threshold value, in an iterative manner, another subset of images different from the first subset is retrieved, and the parameters of the neural network are then updated in accordance with the data represented by the other subset until the threshold value is met.
    Type: Application
    Filed: April 25, 2019
    Publication date: December 19, 2019
    Inventors: Stephen Gould, Samuel Toyer, David Reiner
  • Patent number: 10460175
    Abstract: A method and system for processing multiple frames of a video by a neural network are provided. Two frames of a video may be analyzed to determine if at least a portion of the layer-by-layer processing by a neural network can be skipped or terminated. Processing of a first frame of the video is performed by the neural network. A next frame of the video is processed by the neural network, such that processing of fewer layers (or sets of operations) of the neural network is performed if the first frame and the second frame are substantially similar.
    Type: Grant
    Filed: June 15, 2017
    Date of Patent: October 29, 2019
    Assignee: Amazon Technologies, Inc.
    Inventors: Stephen Gould, Andrea Olgiati
  • Publication number: 20190320644
    Abstract: A rodent box comprising a chamber having at least one side wall, wherein the side wall comprises an aperture to allow access into the chamber and wherein the box is provided with a spacer section extending in a direction away from the chamber.
    Type: Application
    Filed: June 16, 2017
    Publication date: October 24, 2019
    Applicant: SMAM Ltd
    Inventor: Stephen GOULD
  • Publication number: 20190294924
    Abstract: A method of training a computer vision to visually recognize and identify objects includes, in part, supplying N pairs of images to the computer with each pair including first and second images. The first image in each pair includes data representative of a scene as well as an object to be recognized. The second image of each pair includes only the data representative of the scence and thus does not include the object. The training method may further include minimizing a loss function represented by a sum, over all N images, of a conditional probability of finding the object in the i-th image and a conditional probability of not finding the object in the i-th image.
    Type: Application
    Filed: March 21, 2019
    Publication date: September 26, 2019
    Inventors: Stephen Gould, Samuel Toyer, David Reiner
  • Publication number: 20190228108
    Abstract: According to some aspects, techniques for configuring a data processing system are provided that increase flexibility and efficiency of generation of a data profile of a dataset. The data processing system may produce a value census and a validation census of the dataset in separate processing steps. The value census may then be enriched with contents of the validation census by processing the validation census in a manner that allows matching of field-value pairs of the dataset between the two censuses.
    Type: Application
    Filed: January 25, 2018
    Publication date: July 25, 2019
    Applicant: Ab Initio Technology LLC
    Inventors: Joel Gould, Stephen George Rybicki
  • Publication number: 20190156124
    Abstract: Techniques for analyzing stored video upon a request are described. For example, a method of receiving a first application programming interface (API) request to analyze a stored video, the API request to include a location of the stored video and at least one analysis action to perform on the stored video; accessing the location of the stored video to retrieve the stored video; segmenting the accessed video into chunks; processing each chunk with a chunk processor to perform the at least one analysis action, each chunk processor to utilize at least one machine learning model in performing the at least one analysis action; joining the results of the processing of each chunk to generate a final result; storing the final result; and providing the final result to a requestor in response to a second API request is described.
    Type: Application
    Filed: March 20, 2018
    Publication date: May 23, 2019
    Inventors: Nitin SINGHAL, Vivek BHADAURIA, Ranju DAS, Gaurav D. GHARE, Roman GOLDENBERG, Stephen GOULD, Kuang HAN, Jonathan Andrew HEDLEY, Gowtham JEYABALAN, Vasant MANOHAR, Andrea OLGIATI, Stefano STEFANI, Joseph Patrick TIGHE, Praveen Kumar Udayakumar, Renjun ZHANG
  • Publication number: 20190049927
    Abstract: The present disclosure relates to methods and systems for oil and gas field production management. An example system includes a production site and a production sensor configured to obtain information about a process parameter associated with the production site. The system also includes an on-site chemical tank and a mobile delivery vehicle with a chemical delivery system. The chemical delivery system is configured to dispense a chemical. The system also includes a controller that carries out operations, which include receiving, from the production sensor, information indicative of a process parameter value associated with the production site and determining, based on the received information, a chemical delivery request. The operations also include, in response to determining the chemical delivery request, routing the mobile delivery vehicle to the production site and causing the chemical delivery system to dispense the chemical to the on-site chemical tank according to the chemical delivery request.
    Type: Application
    Filed: August 3, 2018
    Publication date: February 14, 2019
    Inventors: Paul Stephen Gould, Douglas Hatton Ford, Derek Wayne Blalock
  • Patent number: 9710696
    Abstract: Apparatuses, methods, and systems for automated cell classification, embryo ranking, and/or embryo categorization are provided. An apparatus includes a classification module configured to apply classifiers to images of one or more cells to determine, for each image, a classification probability associated with each classifier. Each classifier is associated with a distinct first number of cells, and is configured to determine the classification probability for each image based on cell features including one or more machine learned cell features. The classification probability indicates an estimated likelihood that the distinct first number of cells is shown in each image. The classification module is further configured to classify each image as showing a second number of cells based on the distinct first number of cells and the classification probabilities associated therewith. The classification module is implemented in at least one of a memory or a processing device.
    Type: Grant
    Filed: September 17, 2015
    Date of Patent: July 18, 2017
    Assignee: Progyny, Inc.
    Inventors: Yu Wang, Farshid Moussavi, Peter Lorenzen, Stephen Gould
  • Patent number: 9542591
    Abstract: Apparatuses, methods, and systems for automated, non-invasive evaluation of cell activity are provided. In one embodiment, an apparatus includes a hypothesis selection module configured to select a hypothesis from a plurality of hypotheses characterizing one or more cells shown in an image. Each of the plurality of hypotheses includes an inferred characteristic of the one or more cells based on geometric features of the one or more cells shown in the image. The hypothesis selection module is implemented in at least one of a memory or a processing device.
    Type: Grant
    Filed: February 28, 2014
    Date of Patent: January 10, 2017
    Assignee: PROGYNY, INC.
    Inventors: Farshid Moussavi, Yu Wang, Peter Lorenzen, Stephen Gould
  • Publication number: 20160078275
    Abstract: Apparatuses, methods, and systems for automated cell classification, embryo ranking, and/or embryo categorization are provided. An apparatus includes a classification module configured to apply classifiers to images of one or more cells to determine, for each image, a classification probability associated with each classifier. Each classifier is associated with a distinct first number of cells, and is configured to determine the classification probability for each image based on cell features including one or more machine learned cell features. The classification probability indicates an estimated likelihood that the distinct first number of cells is shown in each image. The classification module is further configured to classify each image as showing a second number of cells based on the distinct first number of cells and the classification probabilities associated therewith. The classification module is implemented in at least one of a memory or a processing device.
    Type: Application
    Filed: September 17, 2015
    Publication date: March 17, 2016
    Inventors: Yu Wang, Farshid Moussavi, Peter Lorenzen, Stephen Gould
  • Patent number: 9177192
    Abstract: Apparatuses, methods, and systems for automated cell classification, embryo ranking, and/or embryo categorization are provided. An apparatus includes a classification module configured to apply classifiers to images of one or more cells to determine, for each image, a classification probability associated with each classifier. Each classifier is associated with a distinct first number of cells, and is configured to determine the classification probability for each image based on cell features including one or more machine learned cell features. The classification probability indicates an estimated likelihood that the distinct first number of cells is shown in each image. The classification module is further configured to classify each image as showing a second number of cells based on the distinct first number of cells and the classification probabilities associated therewith. The classification module is implemented in at least one of a memory or a processing device.
    Type: Grant
    Filed: February 28, 2014
    Date of Patent: November 3, 2015
    Assignee: Progyny, Inc.
    Inventors: Yu Wang, Farshid Moussavi, Peter Lorenzen, Stephen Gould
  • Patent number: 9169244
    Abstract: The present invention relates to tyrosine kinase inhibitors that contain a zinc-binding moiety and their use in the treatment of tyrosine related diseases and disorders such as cancer. The said derivatives may further act as HDAC inhibitors.
    Type: Grant
    Filed: March 18, 2013
    Date of Patent: October 27, 2015
    Assignee: Curis, Inc.
    Inventors: Xiong Cai, Changgeng Qian, Stephen Gould, Haixiao Zhai
  • Publication number: 20150284340
    Abstract: The present invention relates to quinazoline containing zinc-binding moiety based derivatives of Formula (IV) below: These compounds have enhanced and unexpected properties as inhibitors of epidermal growth factor receptor tyrosine kinase (EGFR-TK) and are useful in the treatment of EGFR-TK related diseases and disorders such as cancer. These compounds may further act as HDAC inhibitors.
    Type: Application
    Filed: April 15, 2015
    Publication date: October 8, 2015
    Inventors: Changgeng Qian, Xiong Cai, Stephen Gould, Haixiao Zhai
  • Publication number: 20150274678
    Abstract: The present invention relates to quinazoline containing zinc-binding moiety based derivatives of Formula (I) below. These compounds have enhanced and unexpected properties as inhibitors of epidermal growth factor receptor tyrosine kinase (EGFR-TK) and are useful in the treatment of EGFR-TK related diseases and disorders such as cancer. These compounds may further act as HDAC inhibitors.
    Type: Application
    Filed: March 5, 2015
    Publication date: October 1, 2015
    Inventors: Changgeng Qian, Xiong Cai, Stephen Gould
  • Patent number: 9024024
    Abstract: The present invention relates to quinazoline containing zinc-binding moiety based derivatives of Formula (IV) below. These compounds have enhanced and unexpected properties as inhibitors of epidermal growth factor receptor tyrosine kinase (EGFR-TK) and are useful in the treatment of EGFR-TK related diseases and disorders such as cancer. These compounds may further act as HDAC inhibitors.
    Type: Grant
    Filed: November 25, 2013
    Date of Patent: May 5, 2015
    Assignee: Curis, Inc.
    Inventors: Changgeng Qian, Xiong Cai, Stephen Gould, Haixiao Zhai
  • Patent number: 8975401
    Abstract: The present invention relates to quinazoline containing zinc-binding moiety based derivatives of Formula (I) below. These compounds have enhanced and unexpected properties as inhibitors of epidermal growth factor receptor tyrosine kinase (EGFR-TK) and are useful in the treatment of EGFR-TK related diseases and disorders such as cancer. These compounds may further act as HDAC inhibitors.
    Type: Grant
    Filed: May 15, 2013
    Date of Patent: March 10, 2015
    Assignee: Curis, Inc.
    Inventors: Changgeng Qian, Xiong Cai, Stephen Gould
  • Publication number: 20140247973
    Abstract: Apparatuses, methods, and systems for automated, non-invasive evaluation of cell activity are provided. In one embodiment, an apparatus includes a hypothesis selection module configured to select a hypothesis from a plurality of hypotheses characterizing one or more cells shown in an image. Each of the plurality of hypotheses includes an inferred characteristic of the one or more cells based on geometric features of the one or more cells shown in the image. The hypothesis selection module is implemented in at least one of a memory or a processing device.
    Type: Application
    Filed: February 28, 2014
    Publication date: September 4, 2014
    Inventors: Farshid MOUSSAVI, Yu WANG, Peter LORENZEN, Stephen GOULD
  • Publication number: 20140247972
    Abstract: Apparatuses, methods, and systems for automated cell classification, embryo ranking, and/or embryo categorization are provided. An apparatus includes a classification module configured to apply classifiers to images of one or more cells to determine, for each image, a classification probability associated with each classifier. Each classifier is associated with a distinct first number of cells, and is configured to determine the classification probability for each image based on cell features including one or more machine learned cell features. The classification probability indicates an estimated likelihood that the distinct first number of cells is shown in each image. The classification module is further configured to classify each image as showing a second number of cells based on the distinct first number of cells and the classification probabilities associated therewith. The classification module is implemented in at least one of a memory or a processing device.
    Type: Application
    Filed: February 28, 2014
    Publication date: September 4, 2014
    Inventors: YU WANG, FARSHID MOUSSAVI, PETER LORENZEN, STEPHEN GOULD
  • Publication number: 20140221403
    Abstract: The present invention relates to quinazoline containing zinc-binding moiety based derivatives of Formula (IV) below. These compounds have enhanced and unexpected properties as inhibitors of epidermal growth factor receptor tyrosine kinase (EGFR-TK) and are useful in the treatment of EGFR-TK related diseases and disorders such as cancer. These compounds may further act as HDAC inhibitors.
    Type: Application
    Filed: November 25, 2013
    Publication date: August 7, 2014
    Applicant: Curis, Inc.
    Inventors: Changgeng Qian, Xiong Cai, Stephen Gould, Haixiao Zhai