Patents by Inventor Prasanna SATTIGERI
Prasanna SATTIGERI 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: 20240135238Abstract: One or more systems, devices, computer program products and/or computer implemented methods of use provided herein relate to a process of mitigating biased training instances associated with a machine learning model without additional refitting of the machine learning model. A system can comprise a memory that stores computer executable components, and a processor that executed the computer executable components stored in the memory, wherein the computer executable components can comprise a training data influence estimation component and an influence mitigation component. The training data influence estimation component can receive a pre-trained machine learning model and calculate a fairness influence score of training instances on group fairness metrics associated with the pre-trained machine learning model.Type: ApplicationFiled: October 10, 2022Publication date: April 25, 2024Inventors: Prasanna Sattigeri, Soumya Ghosh, Inkit Padhi, Pierre L. Dognin, Kush Raj Varshney
-
Publication number: 20230206114Abstract: One or more group-specific aggregate losses, one or more group-agnostic aggregate losses, and a joint loss are computed. A regularizer loss is computed based on the one or more group-specific aggregate losses and the one or more group-agnostic aggregate losses. One or more group-specific models are trained based on the one or more group-specific aggregate losses. A feature extractor is updated based on the regularizer loss and a joint classifier is updated based on the joint loss.Type: ApplicationFiled: December 29, 2021Publication date: June 29, 2023Inventors: Joshua Ka-Wing Lee, Yuheng Bu, Deepta Rajan, Prasanna Sattigeri, Subhro Das, Rameswar Panda, Gregory Wornell
-
Patent number: 11640532Abstract: 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: GrantFiled: December 3, 2021Date of Patent: May 2, 2023Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Ronny Luss, Pin-Yu Chen, Amit Dhurandhar, Prasanna Sattigeri, Karthikeyan Shanmugam
-
Publication number: 20230021338Abstract: A method for training a machine learning system using conditionally independent training data includes receiving an input dataset (p(x, y, z)). A generative adversarial network, that includes a generator and a first discriminator, uses the input dataset to generate a training data (ps (xf, yf, zf)) by generating the values (xf, yf, zf). The first discriminator determines a first loss (L1) based on (xf, yf, zf) and (x, y, z). A divergence calculator modifies the training data based on a dependence measure (?). The divergence calculator includes a second discriminator and a third discriminator. Modifying the training data includes receiving a reference value ({tilde over (y)}), and computing, by the second discriminator, a second loss (L2) based on (xf, yf, zf) and (xf, {tilde over (y)}, zf). The third discriminator computes a third loss (L3) based on (yf, zf) and ({tilde over (y)}, zf). Further, a fourth loss (L4) is computed based on L2 and L3.Type: ApplicationFiled: July 7, 2021Publication date: January 26, 2023Inventors: Kartik Ahuja, Prasanna Sattigeri, Karthikeyan Shanmugam, Dennis Wei, Murat Kocaoglu, Karthikeyan Natesan Ramamurthy
-
Patent number: 11514318Abstract: Examples described herein provide a computer-implemented method that includes training, by one or more processing devices, a first neural network for classification based on training data in accordance with a first learning objective, the first neural network producing an intermediate feature function and a final feature function as outputs. The computer-implemented method further includes training, by the one or more processing devices, a second neural network for classification based on the intermediate feature function and the final feature function and further based at least in part on target task samples in accordance with a second learning objective. Training the second neural network includes computing maximal correlation functions of each of the intermediate feature function, the final feature function, and the target task samples.Type: GrantFiled: April 8, 2020Date of Patent: November 29, 2022Assignees: INTERNATIONAL BUSINESS MACHINES CORPORATION, MASSACHUSETTS INSTITUTE OF TECHNOLOGYInventors: Joshua Ka-Wing Lee, Prasanna Sattigeri, Gregory Wornell
-
Publication number: 20220092360Abstract: 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: ApplicationFiled: December 3, 2021Publication date: March 24, 2022Applicant: International Business Machines CorporationInventors: Ronny Luss, Pin-Yu Chen, Amit Dhurandhar, Prasanna Sattigeri, Karthikeyan Shanmugam
-
Publication number: 20220012572Abstract: With at least one hardware processor, obtain data specifying: two trained neural network models; and alignment data. With the at least one hardware processor, carry out neuron alignment on the two trained neural network models using the alignment data to obtain two aligned models. With the at least one hardware processor, train a minimal loss curve between the two aligned models. With the at least one hardware processor, select a new model along the minimal loss curve that maximizes accuracy on adversarially perturbed data.Type: ApplicationFiled: July 10, 2020Publication date: January 13, 2022Inventors: Pin-Yu Chen, Payel Das, Igor Melnyk, Prasanna Sattigeri, Rongjie Lai, Norman Tatro
-
Patent number: 11222242Abstract: 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: GrantFiled: August 23, 2019Date of Patent: January 11, 2022Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Ronny Luss, Pin-Yu Chen, Amit Dhurandhar, Prasanna Sattigeri, Karthikeyan Shanmugam
-
Publication number: 20210319303Abstract: Examples described herein provide a computer-implemented method that includes training, by one or more processing devices, a first neural network for classification based on training data in accordance with a first learning objection, the first neural network producing an intermediate feature function and a final feature function as outputs. The computer-implemented method further includes training, by the one or more processing devices, a second neural network for classification based on the intermediate feature function and the final feature function and further based at least in part on target task samples in accordance with a second learning objective. Training the second neural network includes computing maximal correlation functions of each of the intermediate feature function, the final feature function, and the target task samples.Type: ApplicationFiled: April 8, 2020Publication date: October 14, 2021Inventors: Joshua Ka-Wing Lee, Prasanna Sattigeri, Gregory Wornell
-
Publication number: 20210056355Abstract: 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: ApplicationFiled: August 23, 2019Publication date: February 25, 2021Applicant: International Business Machines CorporationInventors: Ronny Luss, Pin-Yu Chen, Amit Dhurandhar, Prasanna Sattigeri, Karthikeyan Shanmugam
-
Patent number: 9875428Abstract: Methods and systems for recovering corrupted/degraded images using approximations obtained from an ensemble of multiple sparse models are disclosed. Sparse models may represent images parsimoniously using elementary patterns from a “dictionary” matrix. Various embodiments of the present disclosure involve simple and computationally efficient dictionary design approach along with low-complexity reconstruction procedure that may use a parallel-friendly table-lookup process. Multiple dictionaries in an ensemble model may be inferred sequentially using greedy forward-selection approach and can incorporate bagging/boosting strategies, taking into account application-specific degradation. Recovery performance obtained using the proposed approaches with image super resolution and compressive recovery can be comparable to or better than existing sparse modeling based approaches, at reduced computational complexity.Type: GrantFiled: March 14, 2014Date of Patent: January 23, 2018Assignee: ARIZONA BOARD OF REGENTS ON BEHALF OF ARIZONA STATE UNIVERSITYInventors: Karthikeyan Ramamurthy, Jayaraman Thiagarajan, Prasanna Sattigeri, Andreas Spanias
-
Publication number: 20160012314Abstract: Methods and systems for recovering corrupted/degraded images using approximations obtained from an ensemble of multiple sparse models are disclosed. Sparse models may represent images parsimoniously using elementary patterns from a “dictionary” matrix. Various embodiments of the present disclosure involve simple and computationally efficient dictionary design approach along with low-complexity reconstruction procedure that may use a parallel-friendly table-lookup process. Multiple dictionaries in an ensemble model may be inferred sequentially using greedy forward-selection approach and can incorporate bagging/boosting strategies, taking into account application-specific degradation. Recovery performance obtained using the proposed approaches with image super resolution and compressive recovery can be comparable to or better than existing sparse modeling based approaches, at reduced computational complexity.Type: ApplicationFiled: March 14, 2014Publication date: January 14, 2016Inventors: Karthikeyan RAMAMURTHY, Jayaraman THIAGARAJAN, Prasanna SATTIGERI, Andreas SPANIAS