Patents by Inventor Mayank Singh
Mayank Singh 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: 20250021869Abstract: A machine learning based system for optimizing training time of a machine learning model is disclosed. The machine learning based system configured to: (a) train the machine learning model on second plurality of data associated with second one or more images corresponding to first one or more products, (b) extract third plurality of data associated with third one or more images corresponding to second one or more products from a database, (c) learn to recognize the third one or more images by fine-tuning the machine learning model trained on the second one or more images, using transfer learning method, (d) fine-tune a subset of the machine learning model to recognize third one or more analyzed images, and (e) analyze fourth one or more images corresponding to the second one or more products using the fine-tuned subset of trained machine learning model trained on third one or more recognized images.Type: ApplicationFiled: July 11, 2023Publication date: January 16, 2025Inventors: Muktabh Mayank Srivastava, Angam Parashar, Ankit Narayan Singh
-
Publication number: 20250023862Abstract: Techniques are described for providing session management functionalities using an access token (e.g., an Open Authorization (OAuth) access token). Upon successful user authentication, a session (e.g., a single sign-on session) is created for the user along with a user identity token that includes information identifying the session. The user identity token is presentable in an access token request sent to an access token issuer authority (e.g., an OAuth server). Upon receiving the access token request, the user identity token is parsed to identify and validate the session against information stored for the session. The validation can include various session management-related checks. If the validation is successful, the token issuer authority generates the access token. In this manner, the access token that is generated is linked to the session. The access token can then be used by an application to gain access to a protected resource.Type: ApplicationFiled: October 1, 2024Publication date: January 16, 2025Applicant: Oracle International CorporationInventors: Mayank Maria, Aarathi Balakrishnan, Dharmvir Singh, Madhu Martin, Vikas Pooven Chathoth, Vamsi Motukuru
-
Publication number: 20240256245Abstract: An example operation may include one or more of receiving, via an application programming interface (API) of a cluster, a persistent volume claim (PVC) with a specification of a software application, identifying a namespace based on a namespace attribute of the PVC, identifying a storage class which is declared as a default storage class for the identified namespace based on the one or more attributes within the PVC and injecting storage criteria of the default storage class into the specification of the software application, and deploying the software application via a node within the identified namespace according to the predefined storage attributes of the default storage class injected into the specification of the software application.Type: ApplicationFiled: January 31, 2023Publication date: August 1, 2024Applicant: International Business Machines CorporationInventors: Neeraj Kumar Kashyap, Ambika Nair, Mayank Singh Sachan, Sandip Amin
-
Patent number: 11875512Abstract: Embodiments are disclosed for training a neural network classifier to learn to more closely align an input image with its attribution map. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a training image comprising a representation of one or more objects, the training image associated with at least one label for the representation of the one or more objects, generating a perturbed training image based on the training image using a neural network, and training the neural network using the perturbed training image by minimizing a combination of classification loss and attribution loss to learn to align an image with its corresponding attribution map.Type: GrantFiled: December 29, 2022Date of Patent: January 16, 2024Assignee: Adobe Inc.Inventors: Mayank Singh, Balaji Krishnamurthy, Nupur Kumari, Puneet Mangla
-
Publication number: 20230401460Abstract: A method of an electronic device for on-device lifestyle recommendations, includes: receiving a user input; determining a fashion context based on the user input; dynamically clustering fashion objects in at least one image stored in the electronic device based on the fashion context; and displaying a lifestyle recommendation including the clustered fashion objects.Type: ApplicationFiled: December 13, 2022Publication date: December 14, 2023Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Mahesh Badari Narayana Gupta, Sreenath DINDUKURTHI, Amit Arvind MANNIKAR, Mayank SINGH
-
Patent number: 11831460Abstract: A method for enhancing a Quality of Experience (QoE) index, by a wearable device, for a user in an Internet of things (IoT) network comprising a plurality of IoT devices is provided. The method includes monitoring the QoE index of the user in the IoT network, detecting a drop in the QoE index of the user, determining whether the dropped QoE index is less than a QoE threshold, in response to determining that the dropped QoE index is less than the QoE threshold, determining at least one IoT device from the plurality of IoT devices that is responsible for the drop in the QoE index of the user using an Artificial intelligence (AI) model, and controlling the IoT device(s) to raise the QoE index of the user above the QoE threshold.Type: GrantFiled: August 17, 2022Date of Patent: November 28, 2023Assignee: Samsung Electronics Co., Ltd.Inventors: Satyajit Anand, Mayank Singh, Ajit S Bopardikar
-
Patent number: 11829880Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating trained neural network with increased robustness against adversarial attacks by utilizing a dynamic dropout routine and/or a cyclic learning rate routine. For example, the disclosed systems can determine a dynamic dropout probability distribution associated with neurons of a neural network. The disclosed systems can further drop neurons from a neural network based on the dynamic dropout probability distribution to help neurons learn distinguishable features. In addition, the disclosed systems can utilize a cyclic learning rate routine to force copy weights of a copy neural network away from weights of an original neural network without decreasing prediction accuracy to ensure that the decision boundaries learned are different.Type: GrantFiled: October 24, 2022Date of Patent: November 28, 2023Assignee: Adobe Inc.Inventors: Mayank Singh, Nupur Kumari, Dhruv Khattar, Balaji Krishnamurthy, Abhishek Sinha
-
Patent number: 11816696Abstract: Machine-learning based multi-step engagement strategy modification is described. Rather than rely heavily on human involvement to manage content delivery over the course of a campaign, the described learning-based engagement system modifies a multi-step engagement strategy, originally created by an engagement-system user, by leveraging machine-learning models. In particular, these leveraged machine-learning models are trained using data describing user interactions with delivered content as those interactions occur over the course of the campaign. Initially, the learning-based engagement system obtains a multi-step engagement strategy created by an engagement-system user. As the multi-step engagement strategy is deployed, the learning-based engagement system randomly adjusts aspects of the sequence of deliveries for some users.Type: GrantFiled: June 23, 2021Date of Patent: November 14, 2023Assignee: Adobe Inc.Inventors: Pankhri Singhai, Sundeep Parsa, Piyush Gupta, Nupur Kumari, Nikaash Puri, Mayank Singh, Eshita Shah, Balaji Krishnamurthy, Akash Rupela
-
Patent number: 11734565Abstract: Embodiments disclosed herein describe systems, methods, and products that generate trained neural networks that are robust against adversarial attacks. During a training phase, an illustrative computer may iteratively optimize a loss function that may include a penalty for ill-conditioned weight matrices in addition to a penalty for classification errors. Therefore, after the training phase, the trained neural network may include one or more well-conditioned weight matrices. The one or more well-conditioned weight matrices may minimize the effect of perturbations within an adversarial input thereby increasing the accuracy of classification of the adversarial input. By contrast, conventional training approaches may merely reduce the classification errors using backpropagation, and, as a result, any perturbation in an input is prone to generate a large effect on the output.Type: GrantFiled: June 3, 2022Date of Patent: August 22, 2023Assignee: Adobe Inc.Inventors: Mayank Singh, Abhishek Sinha, Balaji Krishnamurthy
-
Publication number: 20230239208Abstract: Methods and systems for customizing the characteristic of an electronic device (in the Internet of Things (IoT) environment based on at least one user's physiological state are provided. The method includes identifying context of the electronic device in response to receiving at least one event by the electronic device, wherein the at least one context includes at least one current user activity and an environmental context of a user. The method includes determining the change in a health parameter of the user and re-calibrates the characteristics of an electronic device through the magnitude of change in health parameter from the learning module. The method includes identifying current user activity and an environment context of the user on receiving the event from the electronic device).Type: ApplicationFiled: March 31, 2023Publication date: July 27, 2023Inventors: Satyajit ANAND, Mayank SINGH
-
Publication number: 20230139927Abstract: Embodiments are disclosed for training a neural network classifier to learn to more closely align an input image with its attribution map. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a training image comprising a representation of one or more objects, the training image associated with at least one label for the representation of the one or more objects, generating a perturbed training image based on the training image using a neural network, and training the neural network using the perturbed training image by minimizing a combination of classification loss and attribution loss to learn to align an image with its corresponding attribution map.Type: ApplicationFiled: December 29, 2022Publication date: May 4, 2023Applicant: Adobe Inc.Inventors: Mayank SINGH, Balaji Krishnamurthy, Nupur KUMARI, Puneet MANGLA
-
Patent number: 11631156Abstract: This disclosure includes technologies for image processing, particularly for image generation and editing in a configurable semantic direction. A generative adversarial network is trained with an auxiliary network with an auxiliary task that is designed to disentangle the latent space of the generative adversarial network. Resultantly, a new type of GAN is created to improve image generation or editing in both conditional and unconditional settings.Type: GrantFiled: November 3, 2020Date of Patent: April 18, 2023Assignee: Adobe Inc.Inventors: Mayank Singh, Parth Patel, Nupur Kumari, Balaji Krishnamurthy
-
Publication number: 20230107574Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating trained neural network with increased robustness against adversarial attacks by utilizing a dynamic dropout routine and/or a cyclic learning rate routine. For example, the disclosed systems can determine a dynamic dropout probability distribution associated with neurons of a neural network. The disclosed systems can further drop neurons from a neural network based on the dynamic dropout probability distribution to help neurons learn distinguishable features. In addition, the disclosed systems can utilize a cyclic learning rate routine to force copy weights of a copy neural network away from weights of an original neural network without decreasing prediction accuracy to ensure that the decision boundaries learned are different.Type: ApplicationFiled: October 24, 2022Publication date: April 6, 2023Inventors: Mayank Singh, Nupur Kumari, Dhruv Khattar, Balaji Krishnamurthy, Abhishek Sinha
-
Patent number: 11621890Abstract: Methods and systems for customizing the characteristic of an electronic device (in the Internet of Things (IoT) environment based on at least one user's physiological state are provided. The method includes identifying context of the electronic device in response to receiving at least one event by the electronic device, wherein the at least one context includes at least one current user activity and an environmental context of a user. The method includes determining the change in a health parameter of the user and re-calibrates the characteristics of an electronic device through the magnitude of change in health parameter from the learning module. The method includes identifying current user activity and an environment context of the user on receiving the event from the electronic device).Type: GrantFiled: December 8, 2021Date of Patent: April 4, 2023Assignee: Samsung Electronics Co., Ltd.Inventors: Satyajit Anand, Mayank Singh
-
Publication number: 20230056983Abstract: A method for enhancing a Quality of Experience (QoE) index, by a wearable device, for a user in an Internet of things (IoT) network comprising a plurality of IoT devices is provided. The method includes monitoring the QoE index of the user in the IoT network, detecting a drop in the QoE index of the user, determining whether the dropped QoE index is less than a QoE threshold, in response to determining that the dropped QoE index is less than the QoE threshold, determining at least one IoT device from the plurality of IoT devices that is responsible for the drop in the QoE index of the user using an Artificial intelligence (AI) model, and controlling the IoT device(s) to raise the QoE index of the user above the QoE threshold.Type: ApplicationFiled: August 17, 2022Publication date: February 23, 2023Inventors: Satyajit ANAND, Mayank SINGH, Ajit S BOPARDIKAR
-
Patent number: 11575573Abstract: Methods and systems for customizing the characteristic of an electronic device (in the Internet of Things (IoT) environment based on at least one user's physiological state are provided. The method includes identifying context of the electronic device in response to receiving at least one event by the electronic device, wherein the at least one context includes at least one current user activity and an environmental context of a user. The method includes determining the change in a health parameter of the user and re-calibrates the characteristics of an electronic device through the magnitude of change in health parameter from the learning module. The method includes identifying current user activity and an environment context of the user on receiving the event from the electronic device).Type: GrantFiled: December 8, 2021Date of Patent: February 7, 2023Assignee: Samsung Electronics Co., Ltd.Inventors: Satyajit Anand, Mayank Singh
-
Patent number: 11544495Abstract: Embodiments are disclosed for training a neural network classifier to learn to more closely align an input image with its attribution map. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a training image comprising a representation of one or more objects, the training image associated with at least one label for the representation of the one or more objects, generating a perturbed training image based on the training image using a neural network, and training the neural network using the perturbed training image by minimizing a combination of classification loss and attribution loss to learn to align an image with its corresponding attribution map.Type: GrantFiled: July 10, 2020Date of Patent: January 3, 2023Assignee: Adobe Inc.Inventors: Mayank Singh, Balaji Krishnamurthy, Nupur Kumari, Puneet Mangla
-
Patent number: 11481617Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating trained neural network with increased robustness against adversarial attacks by utilizing a dynamic dropout routine and/or a cyclic learning rate routine. For example, the disclosed systems can determine a dynamic dropout probability distribution associated with neurons of a neural network. The disclosed systems can further drop neurons from a neural network based on the dynamic dropout probability distribution to help neurons learn distinguishable features. In addition, the disclosed systems can utilize a cyclic learning rate routine to force copy weights of a copy neural network away from weights of an original neural network without decreasing prediction accuracy to ensure that the decision boundaries learned are different.Type: GrantFiled: January 22, 2019Date of Patent: October 25, 2022Assignee: Adobe Inc.Inventors: Mayank Singh, Nupur Kumari, Dhruv Khattar, Balaji Krishnamurthy, Abhishek Sinha
-
Publication number: 20220327797Abstract: A method includes optimizing a video quality of a video data stream received by a user in a video conference. A region of at least one frame of the video data stream may be sampled. The sampling rate may be variable based on the rate of change of objects in the video data stream. A video quality metric corresponding to the video quality of the video data stream may be calculated. The video quality of the video data stream may be adjusted based on the video quality metric. Another method includes retrieving a video and detecting one or more moving regions of interest (ROIs). Each of the ROIs is tagged with metadata configured to allow users to interact with the ROI, and the detected ROIs and their corresponding metadata are stored in a file. Based on the file, playback of the video and movement of the ROIs may be synchronized.Type: ApplicationFiled: April 5, 2022Publication date: October 13, 2022Inventors: Iulian Doroftei Calinov, Marek F. Latuskiewicz, Mayank Singh Chaudhary, Meng Zhang, Sergey Sablin, Xingze He, Yu-Chen Sun, Yun Zhang, Addie Louise Marino, Miguel Angel Perez
-
Patent number: 11468314Abstract: Embodiments disclosed herein describe systems, methods, and products that generate trained neural networks that are robust against adversarial attacks. During a training phase, an illustrative computer may iteratively optimize a loss function that may include a penalty for ill-conditioned weight matrices in addition to a penalty for classification errors. Therefore, after the training phase, the trained neural network may include one or more well-conditioned weight matrices. The one or more well-conditioned weight matrices may minimize the effect of perturbations within an adversarial input thereby increasing the accuracy of classification of the adversarial input. By contrast, conventional training approaches may merely reduce the classification errors using backpropagation, and, as a result, any perturbation in an input is prone to generate a large effect on the output.Type: GrantFiled: September 12, 2018Date of Patent: October 11, 2022Assignee: Adobe Inc.Inventors: Mayank Singh, Abhishek Sinha, Balaji Krishnamurthy