Patents by Inventor Sudip Roy

Sudip Roy 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: 11960914
    Abstract: Provided are methods and systems for suggesting an enhanced multimodal interaction. The method for suggesting at least one modality of interaction, includes: identifying, by an electronic device, initiation of an interaction by a user with a first device using a first modality; detecting, by the electronic device, an intent of the user and a state of the user based on the identified initiated interaction; determining, by the electronic device, at least one of a second modality and at least one second device, to continue the initiated interaction, based on the detected intent of the user and the detected state of the user; and providing, by the electronic device, a suggestion to the user to continue the interaction with the first device using the determined second modality, by indicating the second modality on the first device or the at least one second device.
    Type: Grant
    Filed: March 28, 2023
    Date of Patent: April 16, 2024
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Praveen Kumar Guvvakallu Sivamoorthy, Mayank Kumar Tyagi, Navin N, Aravindh N, Sanofer H, Sudip Roy, Arjun Janardhanan Kappatan, Lalith Satya Vara Prasad Medeti, Vrajesh Navinchandra Sejpal, Saumitri Choudhury
  • Publication number: 20230306266
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for optimizing the execution of the operations of a neural network. One of the methods includes obtaining data representing a graph characterizing a plurality of operations of a neural network, wherein each node of the graph characterizes an operation of the neural network and each edge of the graph characterizes data dependency between the operations; processing the data representing the graph using a graph embedding neural network to generate an embedding of the graph; and processing the embedding of the graph using a policy neural network to generate a task output, wherein the task output comprises, for each of the plurality of operations of the neural network, a respective decision for a particular optimization task.
    Type: Application
    Filed: May 22, 2023
    Publication date: September 28, 2023
    Inventors: Yanqi Zhou, Sudip Roy, Amirali Abdolrashidi, Daniel Lin-Kit Wong, Chao Ma, Qiumin Xu, Azalia Mirhoseini
  • Publication number: 20230245662
    Abstract: Embodiments herein disclose a method for an enhanced interaction with a voice assistant using user accessories data by a first electronic device. The method includes detecting an utterance from a first user, where the utterance comprises a data item indicative of an identity of at least one second user. Further, the method includes determining at least one of position information and direction information of at least one wearable electronic device connected to the first electronic device of the first user. Further, the method includes determining the identity of the at least one second user indicated in the utterance of the first user based on at least one of the position and the direction of the at least one wearable electronic device connected to the first electronic device.
    Type: Application
    Filed: November 5, 2022
    Publication date: August 3, 2023
    Inventors: Mayank Kumar TYAGI, Praveen Kumar Guvvakallu Sivamoorthy, Navin N, Vrajesh Navinchandra Sejpal, Aravindh N, Sudip Roy, Sanofer H, Arjun Janardhanan Kappatan, Lalith Satya Vara Prasad Medeti, Saumitri Choudhury
  • Publication number: 20230236858
    Abstract: Provided are methods and systems for suggesting an enhanced multimodal interaction. The method for suggesting at least one modality of interaction, includes: identifying, by an electronic device, initiation of an interaction by a user with a first device using a first modality; detecting, by the electronic device, an intent of the user and a state of the user based on the identified initiated interaction; determining, by the electronic device, at least one of a second modality and at least one second device, to continue the initiated interaction, based on the detected intent of the user and the detected state of the user; and providing, by the electronic device, a suggestion to the user to continue the interaction with the first device using the determined second modality, by indicating the second modality on the first device or the at least one second device.
    Type: Application
    Filed: March 28, 2023
    Publication date: July 27, 2023
    Applicant: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Praveen Kumar GUVVAKALLU SIVAMOORTHY, Mayank Kumar TYAGI, Navin N, Aravindh N, Sanofer H, Sudip ROY, Arjun Janardhanan KAPPATAN, Lalith Satya Vara Prasad MEDETI, Vrajesh Navinchandra SEJPAL, Saumitri CHOUDHURY
  • Publication number: 20230176840
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for compiler optimizations using a compiler optimization network. One of the methods includes receiving an input program, wherein the input program defines a graph of operation modules, wherein each node in the graph is a respective operation module, and each edge between nodes in the graph represents one operation module receiving the output generated by another operation module. The input program is processed by a compiler optimization network comprising a graph-embedding network that is configured to encode operation features and operation dependencies of the operation modules of the input program into a graph embedding representation and a policy network that is configured to generate an optimization action for each of one or more nodes encoded in the graph embedding representation.
    Type: Application
    Filed: June 7, 2021
    Publication date: June 8, 2023
    Inventors: Yanqi Zhou, Sudip Roy, Amirali Abdolrashidi, Daniel Lin-Kit Wong, Chao Ma, Qiumin Xu, Hanxiao Liu, Phitchaya Mangpo Phothilimthana, Shen Wang, Anna Darling Goldie, Azalia Mirhoseini, James Laudon
  • Publication number: 20230169699
    Abstract: The present subject matter refers a virtual object positioning method in an augmented reality (AR) or virtual reality (VR) environment. The method comprises receiving a virtual object for positioning relative to one or more objects in an AR or VR scene. During the positioning, a relative position of the virtual object is detected relative to the one or more objects in the AR or VR scene and a position due to the relative movement is detected. An occurrence of change in a physical characteristic of the virtual object is predicted based on the virtual object crossing a boundary with respect to the one or more objects. It is determined that the virtual object is likely to cross the boundary during the positioning. Upon the determination, a prior alert is generated.
    Type: Application
    Filed: January 24, 2023
    Publication date: June 1, 2023
    Applicant: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Vishal Bhushan JHA, Amit Chowdhury, Ajay Surendranath, Debayan Mukherjee, Raghavan Velappan, Sudip Roy, Swadha Jaiswal, Zunaira Naqvi
  • Patent number: 11657289
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for optimizing the execution of the operations of a neural network. One of the methods includes obtaining data representing a graph characterizing a plurality of operations of a neural network, wherein each node of the graph characterizes an operation of the neural network and each edge of the graph characterizes data dependency between the operations; processing the data representing the graph using a graph embedding neural network to generate an embedding of the graph; and processing the embedding of the graph using a policy neural network to generate a task output, wherein the task output comprises, for each of the plurality of operations of the neural network, a respective decision for a particular optimization task.
    Type: Grant
    Filed: April 3, 2020
    Date of Patent: May 23, 2023
    Assignee: Google LLC
    Inventors: Yanqi Zhou, Sudip Roy, Amirali Abdolrashidi, Daniel Lin-Kit Wong, Chao Ma, Qiumin Xu, Azalia Mirhoseini
  • Publication number: 20230118303
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributing machine learning workloads, e.g., computations for training a neural network or computing an inference using a neural network, across multiple hardware accelerators.
    Type: Application
    Filed: December 15, 2022
    Publication date: April 20, 2023
    Inventors: Jeffrey Adgate Dean, Sudip Roy, Michael Acheson Isard, Aakanksha Chowdhery, Brennan Saeta, Chandramohan Amyangot Thekkath, Daniel William Hurt, Hyeontaek Lim, Laurent El Shafey, Parker Edward Schuh, Paul Ronald Barham, Ruoming Pang, Ryan Sepassi, Sanjay Ghemawat, Yonghui Wu
  • Patent number: 11554175
    Abstract: The disclosure provides a process of designing and optimizing supramolecular therapeutics. The disclosure also provides a method for designing and optimizing antibody drug conjugates.
    Type: Grant
    Filed: July 5, 2017
    Date of Patent: January 17, 2023
    Assignee: AKAMARA THERAPEUTICS, INC.
    Inventors: Shiladitya Sengupta, Sudip Roy, Prithvi Raj Pandey
  • Patent number: 11556381
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributing machine learning workloads, e.g., computations for training a neural network or computing an inference using a neural network, across multiple hardware accelerators.
    Type: Grant
    Filed: May 6, 2022
    Date of Patent: January 17, 2023
    Assignee: Google LLC
    Inventors: Jeffrey Adgate Dean, Sudip Roy, Michael Acheson Isard, Aakanksha Chowdhery, Brennan Saeta, Chandramohan Amyangot Thekkath, Daniel William Hurt, Hyeontaek Lim, Laurent El Shafey, Parker Edward Schuh, Paul Ronald Barham, Ruoming Pang, Ryan Sepassi, Sanjay Ghemawat, Yonghui Wu
  • Publication number: 20220357985
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributing machine learning workloads, e.g., computations for training a neural network or computing an inference using a neural network, across multiple hardware accelerators.
    Type: Application
    Filed: May 6, 2022
    Publication date: November 10, 2022
    Inventors: Jeffrey Adgate Dean, Sudip Roy, Michael Acheson Isard, Aakanksha Chowdhery, Brennan Saeta, Chandramohan Amyangot Thekkath, Daniel William Hurt, Hyeontaek Lim, Laurent El Shafey, Parker Edward Schuh, Paul Ronald Barham, Ruoming Pang, Ryan Sepassi, Sanjay Ghemawat, Yonghui Wu
  • Publication number: 20210248445
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for optimizing the execution of the operations of a neural network. One of the methods includes obtaining data representing a graph characterizing a plurality of operations of a neural network, wherein each node of the graph characterizes an operation of the neural network and each edge of the graph characterizes data dependency between the operations; processing the data representing the graph using a graph embedding neural network to generate an embedding of the graph; and processing the embedding of the graph using a policy neural network to generate a task output, wherein the task output comprises, for each of the plurality of operations of the neural network, a respective decision for a particular optimization task.
    Type: Application
    Filed: April 3, 2020
    Publication date: August 12, 2021
    Inventors: Yanqi Zhou, Sudip Roy, Amirali Abdolrashidi, Daniel Lin-Kit Wong, Chao Ma, Qiumin Xu, Azalia Mirhoseini
  • Patent number: 10633572
    Abstract: The present invention discloses a process for the dissociation of natural gas hydrates comprises injecting additives or hydrate dissociation promoters into the system at the hydrate dissociation temperatures ranging from 283-293 K in conjunction with or without first depressurizing the system to pressures (50%-75%) below the hydrate equilibrium pressure and such leading to the recovery of methane or natural gases.
    Type: Grant
    Filed: January 23, 2017
    Date of Patent: April 28, 2020
    Assignees: Council of Scientific & Industrial Research, Gail (India) Limited
    Inventors: Rajnish Kumar, Sudip Roy, Gaurav Bhattacharjee, Nilesh Choudhary, Asheesh Kumar, Raj Kumar Kashyap, Parivesh Chugh, Nawal Kishore Pande
  • Patent number: 10417439
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a catalog for multiple datasets, the method comprising accessing multiple extant data sets, the extant data sets including data sets that are independently generated and structurally dissimilar; organizing the data sets into collections, each data set in each collection belonging to the collection based on collection data associated with the data set; for each collection of data sets: determining, from a subset of the data sets that belong to the collection, metadata that describe the data sets that belong to the collection, wherein the metadata does not include the collection data, and attributing, to other data sets in the collection, the metadata determined from the subset of data sets; and generating, from the collections of data sets and the determined metadata, a catalog for the multiple datasets.
    Type: Grant
    Filed: April 6, 2017
    Date of Patent: September 17, 2019
    Assignee: Google LLC
    Inventors: Philip Korn, Steven Euijong Whang, Natalya Fridman Noy, Sudip Roy, Neoklis Polyzotis, Alon Yitzchak Halevy, Christopher Olston
  • Publication number: 20190231894
    Abstract: The disclosure provides a process of designing and optimizing supramolecular therapeutics. The disclosure also provides a method for designing and optimizing antibody drug conjugates.
    Type: Application
    Filed: July 5, 2017
    Publication date: August 1, 2019
    Applicant: AKAMARA THERAPEUTICS, INC.
    Inventors: Shiladitya SENGUPTA, Sudip ROY, Prithvi Raj PANEY
  • Publication number: 20190031943
    Abstract: The present invention discloses a process for the dissociation of natural gas hydrates comprises injecting additives or hydrate dissociation promoters into the system at the hydrate dissociation temperatures ranging from 283-293 K in conjunction with or without first depressurizing the system to pressures (50%-75%) below the hydrate equilibrium pressure and such leading to the recovery of methane or natural gases.
    Type: Application
    Filed: January 23, 2017
    Publication date: January 31, 2019
    Inventors: Rajnish Kumar, Sudip Roy, Gaurav Bhattacharjee, Nilesh Choudhary, Asheesh Kumar, Raj Kumar Kashyap, Parivesh Chugh, Nawal Kishore Pande
  • Patent number: 9904584
    Abstract: The described implementations relate to tunable predicate discovery. One implementation is manifest as a method for obtaining a data set and determining anomaly scores for anomalies of an attribute of interest in the data set. The method can also generate a ranked list of predicates based on the anomaly scores and cause at least one of the predicates of the ranked list to be presented.
    Type: Grant
    Filed: April 15, 2015
    Date of Patent: February 27, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Arnd Christian Konig, Igor Dvorkin, Manish Kumar, Sudip Roy
  • Publication number: 20170293671
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a catalog for multiple datasets, the method comprising accessing multiple extant data sets, the extant data sets including data sets that are independently generated and structurally dissimilar; organizing the data sets into collections, each data set in each collection belonging to the collection based on collection data associated with the data set; for each collection of data sets: determining, from a subset of the data sets that belong to the collection, metadata that describe the data sets that belong to the collection, wherein the metadata does not include the collection data, and attributing, to other data sets in the collection, the metadata determined from the subset of data sets; and generating, from the collections of data sets and the determined metadata, a catalog for the multiple datasets.
    Type: Application
    Filed: April 6, 2017
    Publication date: October 12, 2017
    Inventors: Philip Korn, Steven Euijong Whang, Natalya Fridman Noy, Sudip Roy, Neoklis Polyzotis, Alon Yitzchak Halevy, Christopher Olston
  • Publication number: 20160147585
    Abstract: The described implementations relate to tunable predicate discovery. One implementation is manifest as a method for obtaining a data set and determining anomaly scores for anomalies of an attribute of interest in the data set. The method can also generate a ranked list of predicates based on the anomaly scores and cause at least one of the predicates of the ranked list to be presented.
    Type: Application
    Filed: April 15, 2015
    Publication date: May 26, 2016
    Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
    Inventors: Arnd Christian KONIG, Igor DVORKIN, Manish KUMAR, Sudip ROY
  • Patent number: 9201042
    Abstract: Systems and methods are provided for producing fluids with desired concentration factors. According to one embodiment, an arrangement of digital microfluidic (DMF) based electrode platforms are provided. The arrangement may be configured to carry out a sequence of mix steps that may demand storage of resultant fluid mixtures produced in intermediate mix steps. Such sequences of mix steps may be desirable as a result of the decreased demand for initial fluid samples, and reduced wastage.
    Type: Grant
    Filed: November 12, 2010
    Date of Patent: December 1, 2015
    Assignee: INDIAN STATISTICAL INSTITUTE
    Inventors: Bhargab B. Bhattacharya, Sudip Roy, Krishnendu Chakrabarty