Patents by Inventor Karthikeyan SHANMUGAM

Karthikeyan SHANMUGAM 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).

  • Publication number: 20220100817
    Abstract: Techniques regarding root cause analyses based on time series data are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise maintenance component that can detect a cause of failure for a mechanical system by employing a greedy hill climbing process to perform a polynomial number of conditional independence tests to determine a Granger causality between variables from time series data of the mechanical system given a conditioning set.
    Type: Application
    Filed: December 9, 2021
    Publication date: March 31, 2022
    Inventors: Ajil Jalal, Karthikeyan Shanmugam, Bhanukiran Vinzamuri
  • Publication number: 20220092360
    Abstract: In an embodiment, a method for generating contrastive information for a classifier prediction comprises receiving image data representative of an input image, using a deep learning classifier model to predict a first classification for the input image, evaluating the input image using a plurality of classifier functions corresponding to respective high-level features to identify one or more of the high-level features absent from the input image, and identifying, from among the high-level features absent from the input image, a pertinent-negative feature that, if added to the input image, will result in the deep learning classifier model predicting a second classification for the modified input image, the second classification being different from the first classification. In an embodiment, the method includes creating a pertinent-positive image that is a modified version of the input image that has the first classification and fewer than all superpixels of the input image.
    Type: Application
    Filed: December 3, 2021
    Publication date: March 24, 2022
    Applicant: International Business Machines Corporation
    Inventors: Ronny Luss, Pin-Yu Chen, Amit Dhurandhar, Prasanna Sattigeri, Karthikeyan Shanmugam
  • Publication number: 20220037020
    Abstract: Analyzing complex systems by receiving labeled event data describing events occurring in association with a complex system, generating a first machine learning model according to the distribution of labeled event data, receiving state variable transition data describing state variable transitions occurring in association with a complex system, training a second machine learning model according to a combination of a distribution of state variable transitions and the first machine learning model, and using the second machine learning model to predict the effects of events upon state variables within the complex system according to new state variable transition and new labeled event data.
    Type: Application
    Filed: July 30, 2020
    Publication date: February 3, 2022
    Inventors: Debarun Bhattacharjya, Tian Gao, Nicholas Scott Mattei, Karthikeyan Shanmugam, Dharmashankar Subramanian, Kush Raj Varshney
  • Patent number: 11238129
    Abstract: Techniques regarding root cause analyses based on time series data are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise maintenance component that can detect a cause of failure for a mechanical system by employing a greedy hill climbing process to perform a polynomial number of conditional independence tests to determine a Granger causality between variables from time series data of the mechanical system given a conditioning set.
    Type: Grant
    Filed: December 11, 2019
    Date of Patent: February 1, 2022
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Ajil Jalal, Karthikeyan Shanmugam, Bhanukiran Vinzamuri
  • Patent number: 11222242
    Abstract: In an embodiment, a method for generating contrastive information for a classifier prediction comprises receiving image data representative of an input image, using a deep learning classifier model to predict a first classification for the input image, evaluating the input image using a plurality of classifier functions corresponding to respective high-level features to identify one or more of the high-level features absent from the input image, and identifying, from among the high-level features absent from the input image, a pertinent-negative feature that, if added to the input image, will result in the deep learning classifier model predicting a second classification for the modified input image, the second classification being different from the first classification. In an embodiment, the method includes creating a pertinent-positive image that is a modified version of the input image that has the first classification and fewer than all superpixels of the input image.
    Type: Grant
    Filed: August 23, 2019
    Date of Patent: January 11, 2022
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Ronny Luss, Pin-Yu Chen, Amit Dhurandhar, Prasanna Sattigeri, Karthikeyan Shanmugam
  • Publication number: 20210397988
    Abstract: This disclosure provides a method, apparatus and computer program product to create a full homomorphic encryption (FHE)-friendly machine learning model. The approach herein leverages a knowledge distillation framework wherein the FHE-friendly (student) ML model closely mimics the predictions of a more complex (teacher) model, wherein the teacher model is one that, relative to the student model, is more complex and that is pre-trained on large datasets. In the approach herein, the distillation framework uses the more complex teacher model to facilitate training of the FHE-friendly model, but using synthetically-generated training data in lieu of the original datasets used to train the teacher.
    Type: Application
    Filed: June 22, 2020
    Publication date: December 23, 2021
    Applicant: International Business Machines Corporation
    Inventors: Kanthi Sarpatwar, Nalini K. Ratha, Karthikeyan Shanmugam, Karthik Nandakumar, Sharathchandra Pankanti, Roman Vaculin, James Thomas Rayfield
  • Publication number: 20210383194
    Abstract: A computer-implemented method is presented for learning relationships between multiple event types by employing a multi-channel neural graphical event model (MCN-GEM). The method includes receiving, by a computing device, time-stamped, asynchronous, irregularly spaced event epochs, generating, by the computing device, at least one fake epoch between each inter-event interval, wherein fake epochs represent negative evidence, feeding the event epochs and the at least one fake epoch into long short term memory (LSTM) cells, computing hidden states for each of the event epochs and the at least one fake epoch, feeding the hidden states into spatial and temporal attention models, and employing an average attention across all event epochs to generate causal graphs representing causal relationships between all the event epochs.
    Type: Application
    Filed: June 8, 2020
    Publication date: December 9, 2021
    Inventors: Dharmashankar Subramanian, Tian Gao, Karthikeyan Shanmugam, Debarun Bhattacharjya
  • Publication number: 20210376995
    Abstract: A technique for computationally-efficient privacy-preserving homomorphic inferencing against a decision tree. Inferencing is carried out by a server against encrypted data points provided by a client. Fully homomorphic computation is enabled with respect to the decision tree by intelligently configuring the tree and the real number-valued features that are applied to the tree. To that end, and to the extent the decision tree is unbalanced, the server first balances the tree. A cryptographic packing scheme is then applied to the balanced decision tree and, in particular, to one or more entries in at least one of: an encrypted feature set, and a threshold data set, that are to be used during the decision tree evaluation process. Upon receipt of an encrypted data point, homomorphic inferencing on the configured decision tree is performed using a highly-accurate approximation comparator, which implements a “soft” membership recursive computation on real numbers, all in an oblivious manner.
    Type: Application
    Filed: May 27, 2020
    Publication date: December 2, 2021
    Applicant: International Business Machines Corporation
    Inventors: Nalini K. Ratha, Kanthi Sarpatwar, Karthikeyan Shanmugam, Sharathchandra Pankanti, Karthik Nandakumar, Roman Vaculin
  • Publication number: 20210342685
    Abstract: A computer-implemented method, system, and non-transitory computer-readable storage medium for enhancing performance of a first model. The first model is trained with a training data set. A second model receives the training data set associated with the first model. The second model provides the first model with a hardness value associated with prediction of each data point of the training data set. The first model determines a confidence value regarding predicting each data point based on the training data set, and determines a ratio of the hardness value of a prediction of each data point by the second model with respect to the confidence value of the first model. The first model is retrained with a re-weighted training data set when the determined ratio is lower than a value of ?.
    Type: Application
    Filed: April 29, 2020
    Publication date: November 4, 2021
    Inventors: Amit Dhurandhar, Karthikeyan Shanmugam, Ronny Luss
  • Publication number: 20210344478
    Abstract: A method, apparatus and computer program product for homomorphic inference on a decision tree (DT) model. In lieu of HE-based inferencing on the decision tree, the inferencing instead is performed on a neural network (NN), which acts as a surrogate. To this end, the neural network is trained to learn DT decision boundaries, preferably without using the original DT model data training points. During training, a random data set is applied to the DT, and expected outputs are recorded. This random data set and the expected outputs are then used to train the neural network such that the outputs of the neural network match the outputs expected from applying the original data set to the DT. Preferably, the neural network has low depth, just a few layers. HE-based inferencing on the decision tree is done using HE inferencing on the shallow neural network. The latter is computationally-efficient and is carried without the need for bootstrapping.
    Type: Application
    Filed: April 30, 2020
    Publication date: November 4, 2021
    Applicant: International Business Machines Corporation
    Inventors: Kanthi Sarpatwar, Nalini K. Ratha, Karthikeyan Shanmugam, Karthik Nandakumar, Sharathchandra Pankanti, Roman Vaculin
  • Publication number: 20210319353
    Abstract: An example operation includes one or more of computing, by a data owner node, updated gradients on a loss function based on a batch of private data and previous parameters of a machine learning model associated with a blockchain, encrypting, by the data owner node, update information, recording, by the data owner, the encrypted update information as a new transaction on the blockchain, and providing the update information for an audit.
    Type: Application
    Filed: April 9, 2020
    Publication date: October 14, 2021
    Inventors: Kanthi Sarpatwar, Karthikeyan Shanmugam, Venkata Sitaramagiridharganesh Ganapavarapu, Roman Vaculin
  • Publication number: 20210182358
    Abstract: Techniques regarding root cause analyses based on time series data are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise maintenance component that can detect a cause of failure for a mechanical system by employing a greedy hill climbing process to perform a polynomial number of conditional independence tests to determine a Granger causality between variables from time series data of the mechanical system given a conditioning set.
    Type: Application
    Filed: December 11, 2019
    Publication date: June 17, 2021
    Inventors: Ajil Jalal, Karthikeyan Shanmugam, Bhanukiran Vinzamuri
  • Publication number: 20210056355
    Abstract: In an embodiment, a method for generating contrastive information for a classifier prediction comprises receiving image data representative of an input image, using a deep learning classifier model to predict a first classification for the input image, evaluating the input image using a plurality of classifier functions corresponding to respective high-level features to identify one or more of the high-level features absent from the input image, and identifying, from among the high-level features absent from the input image, a pertinent-negative feature that, if added to the input image, will result in the deep learning classifier model predicting a second classification for the modified input image, the second classification being different from the first classification. In an embodiment, the method includes creating a pertinent-positive image that is a modified version of the input image that has the first classification and fewer than all superpixels of the input image.
    Type: Application
    Filed: August 23, 2019
    Publication date: February 25, 2021
    Applicant: International Business Machines Corporation
    Inventors: Ronny Luss, Pin-Yu Chen, Amit Dhurandhar, Prasanna Sattigeri, Karthikeyan Shanmugam
  • Publication number: 20200394470
    Abstract: An example operation may include one or more of generating, by a training participant client, a plurality of transaction proposals, each of the plurality of transaction proposals corresponding to a training iteration for machine learning model training related to stochastic gradient descent, the machine learning model training comprising a plurality of training iterations, the transaction proposals comprising a gradient calculation performed by the training participant client, transferring the plurality of transaction proposals to one or more endorser nodes or peers each comprising a verify gradient smart contract, executing, by each of the endorser nodes or peers, the verify gradient smart contract; and providing endorsements corresponding to the plurality of transaction proposals to the training participation client.
    Type: Application
    Filed: June 12, 2019
    Publication date: December 17, 2020
    Inventors: Venkata Sitaramagiridharganesh Ganapavarapu, Kanthi Sarpatwar, Karthikeyan Shanmugam, Roman Vaculin
  • Publication number: 20200394471
    Abstract: An example operation may include one or more of generating, by a training participant client comprising a training dataset, a plurality of transaction proposals that each correspond to a training iteration for machine learning model training related to stochastic gradient descent, the machine learning model training comprising a plurality of training iterations, the transaction proposals comprising a gradient calculation performed by the training participant client, a batch from the private dataset, a loss function, and an original model parameter, receiving, by one or more endorser nodes of peers of a blockchain network, the plurality of transaction proposals, and evaluating each transaction proposal.
    Type: Application
    Filed: June 12, 2019
    Publication date: December 17, 2020
    Inventors: Venkata Sitaramagiridharganesh Ganapavarapu, Kanthi Sarpatwar, Karthikeyan Shanmugam, Roman Vaculin
  • Publication number: 20200394552
    Abstract: An example operation may include one or more of generating, by a plurality of training participant clients, gradient calculations for machine learning model training, each of the training participant clients comprising a training dataset, converting, by a training aggregator coupled to the plurality of training participant clients, the gradient calculations to a plurality of transaction proposals, receiving, by one or more endorser nodes or peers of a blockchain network, the plurality of transaction proposals, executing, by each of the endorser nodes or peers, a verify gradient smart contract, and providing endorsements corresponding to the plurality of transaction proposals to the training aggregator.
    Type: Application
    Filed: June 12, 2019
    Publication date: December 17, 2020
    Inventors: Venkata Sitaramagiridharganesh Ganapavarapu, Kanthi Sarpatwar, Karthikeyan Shanmugam, Roman Vaculin
  • Publication number: 20200193243
    Abstract: A method, system, and computer program product, including generating a contrastive explanation for a decision of a classifier trained on structured data, highlighting an important feature that justifies the decision, and determining a minimal set of new values for features that alter the decision.
    Type: Application
    Filed: December 12, 2018
    Publication date: June 18, 2020
    Inventors: Amit Dhurandhar, Pin-Yu Chen, Karthikeyan Shanmugam, Tejaswini Pedapati, Avinash Balakrishnan, Ruchir Puri
  • Publication number: 20200167642
    Abstract: A method, system, and computer program product, including generating, using a linear probe, confidence scores through flattened intermediate representations and theoretically-justified weighting of samples during a training of the simple model using the confidence scores of the intermediate representations.
    Type: Application
    Filed: November 28, 2018
    Publication date: May 28, 2020
    Inventors: Amit Dhurandhar, Karthikeyan Shanmugam, Ronny Luss, Peder Andreas Olsen
  • Publication number: 20200167641
    Abstract: A method, system, and computer program product, including highlighting a minimally sufficient component in an input to justify a classification, identifying contrastive characteristics or features that are minimally and critically absent, maintaining the classification and distinguishing it from a second input that is closest to the classification but is identified as a second classification.
    Type: Application
    Filed: November 28, 2018
    Publication date: May 28, 2020
    Inventors: Amit Dhurandhar, Pin-Yu Chen, Ronny Luss, Karthikeyan Shanmugam, Payel Das
  • Publication number: 20190287027
    Abstract: An example operation may include one or more of generating a hashed summary including hashes of one or more of a validation data set and hashes of data points chosen in previous iterations from producer nodes, and exposing the hashed summary to a plurality of producer nodes, receiving, iteratively, a plurality of requests from the plurality of producer nodes, respectively, where each request identifies a marginal value provided by a hash of a data sample available to a producer node, selecting a request received from a producer node based on a marginal value associated with the request, retrieving hashed data of the producer node associated with the selected request, and aggregating the hashed data of the producer node with the summary of hashes generated at one or more previous iterations to produce an updated summary, and storing the updated summary via a data block of a distributed ledger.
    Type: Application
    Filed: March 15, 2018
    Publication date: September 19, 2019
    Inventors: Michele M. Franceschini, Ashish Jagmohan, Kanthi Sarpatwar, Karthikeyan SHANMUGAM, Roman Vaculin