Patents by Inventor Sachin Subhash TALATHI

Sachin Subhash TALATHI 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: 10510146
    Abstract: A method for processing an input in an artificial neural network (ANN) includes receiving, at an operator layer of a set of operator layers, a first feature value based on the input from a decoder convolutional layer of a decoder. The operator layer also receives a second feature value based on the input from an encoder convolutional layer of a encoder. The method also includes determining, at the operator layer, a third feature value based on the input by performing an element-wise operation with the first feature value based on the input and the second feature value based on the input. The method transmits, from the operator layer, the third feature value based on the input to an encoder layer that is subsequent to the encoder convolutional layer. The method generates an output based on the third feature value based on the input.
    Type: Grant
    Filed: February 1, 2017
    Date of Patent: December 17, 2019
    Assignee: Qualcomm Incorporated
    Inventor: Sachin Subhash Talathi
  • Patent number: 10474949
    Abstract: A method for classifying an object includes applying multiple confidence values to multiple objects. The method also includes determining a metric based on the multiple confidence values. The method further includes determining a classification of a first object from the multiple objects based on a knowledge-graph when the metric is above a threshold.
    Type: Grant
    Filed: October 30, 2014
    Date of Patent: November 12, 2019
    Assignee: Qualcomm Incorporated
    Inventors: Somdeb Majumdar, Regan Blythe Towal, Sachin Subhash Talathi, David Jonathan Julian, Venkata Sreekanta Reddy Annapureddy
  • Patent number: 10408852
    Abstract: A system is provided to automatically monitor and control the operation of a microfluidic device using machine learning technology. The system receives images of a channel of a microfluidic device collected by a camera during operation of the microfluidic device. Upon receiving an image, the system applies a classifier to the image to classify the operation of the microfluidic device as normal, in which no adjustment to the operation is needed, or as abnormal, in which an adjustment to the operation is needed. When an image is classified as normal, the system may make no adjustment to the microfluidic device. If, however, an image is classified as abnormal, the system may output an indication that the operation is abnormal, output an indication of a needed adjustment, or control the microfluidic device to make the needed adjustment.
    Type: Grant
    Filed: April 26, 2017
    Date of Patent: September 10, 2019
    Assignee: Lawrence Livermore National Security, LLC
    Inventors: Brian Giera, Eric Duoss, Du Nguyen, William Smith, Sachin Subhash Talathi, Aaron Creighton Wilson, Congwang Ye
  • Publication number: 20190234976
    Abstract: A system is provided to automatically monitor and control the operation of a microfluidic device using machine learning technology. The system receives images of a channel of a microfluidic device collected by a camera during operation of the microfluidic device. Upon receiving an image, the system applies a classifier to the image to classify the operation of the microfluidic device as normal, in which no adjustment to the operation is needed, or as abnormal, in which an adjustment to the operation is needed. When an image is classified as normal, the system may make no adjustment to the microfluidic device. If, however, an image is classified as abnormal, the system may output an indication that the operation is abnormal, output an indication of a needed adjustment, or control the microfluidic device to make the needed adjustment.
    Type: Application
    Filed: April 5, 2019
    Publication date: August 1, 2019
    Inventors: Brian Giera, Eric B. Duoss, Du Nguyen, William Smith, Sachin Subhash Talathi, Aaron Creighton Wilson, Congwang Ye
  • Patent number: 10339447
    Abstract: A method for selecting a reduced number of model neurons in a neural network includes generating a first sparse set of non-zero decoding vectors. Each of the decoding vector is associated with a synapse between a first neuron layer and a second neuron layer. The method further includes implementing the neural network only with selected model neurons in the first neuron layer associated with the non-zero decoding vectors.
    Type: Grant
    Filed: July 31, 2014
    Date of Patent: July 2, 2019
    Assignee: QUALCOMM Incorporated
    Inventors: Sachin Subhash Talathi, David Jonathan Julian, Venkata Sreekanta Reddy Annapureddy
  • Patent number: 10332028
    Abstract: A method for improving performance of a trained machine learning model includes adding a second classifier with a second objective function to a first classifier with a first objective function. Rather than minimizing a function of errors for the first classifier, the second objective function is used to directly reduce the number errors of the first classifier.
    Type: Grant
    Filed: September 23, 2015
    Date of Patent: June 25, 2019
    Assignee: QUALCOMM Incorporated
    Inventors: Sachin Subhash Talathi, Aniket Vartak
  • Patent number: 10275719
    Abstract: Hyper-parameters are selected for training a deep convolutional network by selecting a number of network architectures as part of a database. Each of the network architectures includes one or more local logistic regression layer and is trained to generate a corresponding validation error that is stored in the database. A threshold error for identifying a good set of network architectures and a bad set of network architectures may be estimated based on validation errors in the database. The method also includes choosing a next potential hyper-parameter, corresponding to a next network architecture, based on a metric that is a function of the good set of network architectures. The method further includes selecting a network architecture, from among next network architectures, with a lowest validation error.
    Type: Grant
    Filed: September 8, 2015
    Date of Patent: April 30, 2019
    Assignee: QUALCOMM Incorporated
    Inventors: Sachin Subhash Talathi, David Jonathan Julian
  • Publication number: 20180311663
    Abstract: A system is provided to automatically monitor and control the operation of a microfluidic device using machine learning technology. The system receives images of a channel of a microfluidic device collected by a camera during operation of the microfluidic device. Upon receiving an image, the system applies a classifier to the image to classify the operation of the microfluidic device as normal, in which no adjustment to the operation is needed, or as abnormal, in which an adjustment to the operation is needed. When an image is classified as normal, the system may make no adjustment to the microfluidic device. If, however, an image is classified as abnormal, the system may output an indication that the operation is abnormal, output an indication of a needed adjustment, or control the microfluidic device to make the needed adjustment.
    Type: Application
    Filed: April 26, 2017
    Publication date: November 1, 2018
    Inventors: Brian Giera, Eric Duoss, Du Nguyen, William Smith, Sachin Subhash Talathi, Aaron Creighton Wilson, Congwang Ye
  • Patent number: 10043112
    Abstract: A method for image processing includes determining features of multiple stored images from a pre-trained deep convolutional network. The method also includes clustering each image of the multiple stored images based on the determined features.
    Type: Grant
    Filed: October 30, 2014
    Date of Patent: August 7, 2018
    Assignee: QUALCOMM Incorporated
    Inventors: Sachin Subhash Talathi, David Jonathan Julian
  • Publication number: 20180101957
    Abstract: A method for processing an input in an artificial neural network (ANN) includes receiving, at an operator layer of a set of operator layers, a first feature value based on the input from a decoder convolutional layer of a decoder. The operator layer also receives a second feature value based on the input from an encoder convolutional layer of a encoder. The method also includes determining, at the operator layer, a third feature value based on the input by performing an element-wise operation with the first feature value based on the input and the second feature value based on the input. The method transmits, from the operator layer, the third feature value based on the input to an encoder layer that is subsequent to the encoder convolutional layer. The method generates an output based on the third feature value based on the input.
    Type: Application
    Filed: February 1, 2017
    Publication date: April 12, 2018
    Inventor: Sachin Subhash TALATHI
  • Publication number: 20170061326
    Abstract: A method for improving performance of a trained machine learning model includes adding a second classifier with a second objective function to a first classifier with a first objective function. Rather than minimizing a function of errors for the first classifier, the second objective function is used to directly reduce the number errors of the first classifier.
    Type: Application
    Filed: September 23, 2015
    Publication date: March 2, 2017
    Inventors: Sachin Subhash TALATHI, Aniket VARTAK
  • Publication number: 20160328644
    Abstract: A method of adaptively selecting a configuration for a machine learning process includes determining current system resources and performance specifications of a current system. A new configuration for the machine learning process is determined based at least in part on the current system resources and the performance specifications. The method also includes dynamically selecting between a current configuration and the new configuration based at least in part on the current system resources and the performance specifications.
    Type: Application
    Filed: October 8, 2015
    Publication date: November 10, 2016
    Inventors: Dexu LIN, Venkata Sreekanta Reddy ANNAPUREDDY, Sachin Subhash TALATHI, Mark STASKAUSKAS, Aniket VARTAK, Regan Blythe TOWAL, David Jonathan JULIAN, Anthony SARAH
  • Publication number: 20160224903
    Abstract: Hyper-parameters are selected for training a deep convolutional network by selecting a number of network architectures as part of a database. Each of the network architectures includes one or more local logistic regression layer and is trained to generate a corresponding validation error that is stored in the database. A threshold error for identifying a good set of network architectures and a bad set of network architectures may be estimated based on validation errors in the database. The method also includes choosing a next potential hyper-parameter, corresponding to a next network architecture, based on a metric that is a function of the good set of network architectures. The method further includes selecting a network architecture, from among next network architectures, with a lowest validation error.
    Type: Application
    Filed: September 8, 2015
    Publication date: August 4, 2016
    Inventors: Sachin Subhash TALATHI, David Jonathan JULIAN
  • Publication number: 20160055409
    Abstract: A method for classifying an object includes applying multiple confidence values to multiple objects. The method also includes determining a metric based on the multiple confidence values. The method further includes determining a classification of a first object from the multiple objects based on a knowledge-graph when the metric is above a threshold.
    Type: Application
    Filed: October 30, 2014
    Publication date: February 25, 2016
    Inventors: Somdeb MAJUMDAR, Regan Blythe TOWAL, Sachin Subhash TALATHI, David Jonathan JULIAN, Venkata Sreekanta Reddy ANNAPUREDDY
  • Publication number: 20150269485
    Abstract: Neuron state updates are computed with spiking models with map based updates and at least one reset mechanism. Back propagation is applied on spike times to compute weight updates.
    Type: Application
    Filed: September 15, 2014
    Publication date: September 24, 2015
    Inventors: David Jonathan JULIAN, Sachin Subhash TALATHI
  • Publication number: 20150254532
    Abstract: A method for image processing includes determining features of multiple stored images from a pre-trained deep convolutional network. The method also includes clustering each image of the multiple stored images based on the determined features.
    Type: Application
    Filed: October 30, 2014
    Publication date: September 10, 2015
    Inventors: Sachin Subhash TALATHI, David Jonathan JULIAN
  • Publication number: 20150206050
    Abstract: A method for selecting a neuron model with a user defined firing rate for operating in a neural network includes selecting the neuron model based on a selected firing rate bandwidth.
    Type: Application
    Filed: July 31, 2014
    Publication date: July 23, 2015
    Inventors: Sachin Subhash TALATHI, David Jonathan JULIAN, Venkata Sreekanta Reddy ANNAPUREDDY
  • Publication number: 20150206048
    Abstract: A method for selecting a reduced number of model neurons in a neural network includes generating a first sparse set of non-zero decoding vectors. Each of the decoding vector is associated with a synapse between a first neuron layer and a second neuron layer. The method further includes implementing the neural network only with selected model neurons in the first neuron layer associated with the non-zero decoding vectors.
    Type: Application
    Filed: July 31, 2014
    Publication date: July 23, 2015
    Inventors: Sachin Subhash TALATHI, David Jonathan JULIAN, Venkata Sreekanta Reddy ANNAPUREDDY