-
公开(公告)号：US20240005146A1
公开(公告)日：2024-01-04
申请号：US17855085
申请日：2022-06-30
Applicant: Adobe Inc. , Delhi Technological University
Inventor： Tanay Anand , Piyush Gupta , Pinkesh Badjatiya , Nikaash Puri , Jayakumar Subramanian , Balaji Krishnamurthy , Chirag Singla , Rachit Bansal , Anil Singh Parihar
CPC classification number: G06N3/08 , G06N3/0445
Abstract: In some embodiments, techniques for extracting high-value sequential patterns are provided. For example, a process may involve training a machine learning model to learn a state-action map that contains high-utility sequential patterns; extracting at least one high-utility sequential pattern from the trained machine learning model; and causing a user interface of a computing environment to be modified based on information from the at least one high-utility sequential pattern.
-
公开(公告)号：US20230342425A1
公开(公告)日：2023-10-26
申请号：US17659983
申请日：2022-04-20
Applicant: ADOBE INC.
Inventor： Tanay Anand , Pinkesh Badjatiya , Sriyash Poddar , Jayakumar Subramanian , Georgios Theocharous , Balaji Krishnamurthy
CPC classification number: G06K9/6251 , G06N3/088
Abstract: Systems and methods for machine learning are described. Embodiments of the present disclosure receive state information that describes a state of a decision making agent in an environment; compute an action vector from an action embedding space based on the state information using a policy neural network of the decision making agent, wherein the policy neural network is trained using reinforcement learning based on a topology loss that constrains changes in a mapping between an action set and the action embedding space; and perform an action that modifies the state of the decision making agent in the environment based on the action vector, wherein the action is selected based on the mapping.
-
公开(公告)号：US20230169271A1
公开(公告)日：2023-06-01
申请号：US17644856
申请日：2021-12-17
Applicant: ADOBE INC.
Inventor： Shashank Shailabh , Madhur Panwar , Milan Aggarwal , Pinkesh Badjatiya , Simra Shahid , Nikaash Puri , S Sejal Naidu , Sharat Chandra Racha , Balaji Krishnamurthy , Ganesh Karbhari Palwe
IPC: G06F40/289 , G06F40/40 , G06F40/30
CPC classification number: G06F40/289 , G06F40/40 , G06F40/30
Abstract: Systems and methods for topic modeling are described. The systems and methods include encoding words of a document using an embedding matrix to obtain word embeddings for the document. The words of the document comprise a subset of words in a vocabulary, and the embedding matrix is trained as part of a topic attention network based on a plurality of topics. The systems and methods further include encoding a topic-word distribution matrix using the embedding matrix to obtain a topic embedding matrix. The topic-word distribution matrix represents relationships between the plurality of topics and the words of the vocabulary. The systems and methods further include computing a topic context matrix based on the topic embedding matrix and the word embeddings and identifying a topic for the document based on the topic context matrix.
-
公开(公告)号：US20230153534A1
公开(公告)日：2023-05-18
申请号：US17526824
申请日：2021-11-15
Applicant: ADOBE INC.
Inventor： Rachit Bansal , Milan Aggarwal , Sumit Bhatia , Jivat Neet Kaur , Balaji Krishnamurthy
IPC: G06F40/295 , G06F16/332 , G06N20/00
CPC classification number: G06F40/295 , G06F16/3329 , G06N20/00
Abstract: Methods and systems are provided for facilitating generation and utilization of a commonsense contextualizing machine learning (ML) model, in accordance with embodiments described herein. In embodiments, a commonsense contextual ML model is trained by fine-tuning a pre-trained language model using a set of training path-sentence pairs. Each training path-sentence pair includes a commonsense path, identified via a commonsense knowledge graph, and a natural language sentence identified as contextually related to the commonsense path. The trained commonsense contextualizing ML model can then be used to generate a commonsense inference path for a text input. Such a commonsense inference path can include a sequence of entities and relations that provide commonsense context to the text input. Thereafter, the commonsense inference path can be provided to a natural language processing system for use in performing a natural language processing task.
-
公开(公告)号：US11645786B2
公开(公告)日：2023-05-09
申请号：US17654529
申请日：2022-03-11
Applicant: Adobe Inc.
Inventor： Meet Patel , Mayur Hemani , Karanjeet Singh , Amit Gupta , Apoorva Gupta , Balaji Krishnamurthy
CPC classification number: G06T9/002 , G06N3/08 , G06T7/0002 , G06T2207/20081 , G06T2207/20084 , G06T2207/20224
Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing deep learning to intelligently determine compression settings for compressing a digital image. For instance, the disclosed system utilizes a neural network to generate predicted perceptual quality values for compression settings on a compression quality scale. The disclosed system fits the predicted compression distortions to a perceptual distortion characteristic curve for interpolating predicted perceptual quality values across the compression settings on the compression quality scale. Additionally, the disclosed system then performs a search over the predicted perceptual quality values for the compression settings along the compression quality scale to select a compression setting based on a perceptual quality threshold. The disclosed system generates a compressed digital image according to compression parameters for the selected compression setting.
-
Patent Agency Ranking
公开(公告)号：US20230139927A1
公开(公告)日：2023-05-04
申请号：US18148256
申请日：2022-12-29
Applicant: Adobe Inc.
Inventor： Mayank SINGH , Balaji Krishnamurthy , Nupur KUMARI , Puneet MANGLA
IPC: G06T7/11 , G06N3/08 , G06N3/04 , G06F18/214 , G06F18/21 , G06V10/774 , G06V10/82
Abstract: 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.
-
公开(公告)号：US11538051B2
公开(公告)日：2022-12-27
申请号：US16168288
申请日：2018-10-23
Applicant: Adobe Inc.
Inventor： Praveen Kumar Goyal , Piyush Gupta , Nikaash Puri , Balaji Krishnamurthy , Arun Kumar , Atul Kumar Shrivastava
Abstract: Techniques are described for machine learning-based generation of target segments is leveraged in a digital medium environment. A segment targeting system generates training data to train a machine learning model to predict strength of correlation between a set of users and a defined demographic. Further, a machine learning model is trained with visit statistics for the users to predict the likelihood that the users will visit a particular digital content platform. Those users with the highest predicted correlation with the defined demographic and the highest likelihood to visit the digital content platform can be selected and placed within a target segment, and digital content targeted to the defined demographic can be delivered to users in the target segment.
-
78.发明授权公开(公告)号：US11481617B2
公开(公告)日：2022-10-25
申请号：US16253561
申请日：2019-01-22
Applicant: Adobe Inc.
Inventor： Mayank Singh , Nupur Kumari , Dhruv Khattar , Balaji Krishnamurthy , Abhishek Sinha
Abstract: 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.
-
公开(公告)号：US11335033B2
公开(公告)日：2022-05-17
申请号：US17032704
申请日：2020-09-25
Applicant: Adobe Inc.
Inventor： Meet Patel , Mayur Hemani , Karanjeet Singh , Amit Gupta , Apoorva Gupta , Balaji Krishnamurthy
Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing deep learning to intelligently determine compression settings for compressing a digital image. For instance, the disclosed system utilizes a neural network to generate predicted perceptual quality values for compression settings on a compression quality scale. The disclosed system fits the predicted compression distortions to a perceptual distortion characteristic curve for interpolating predicted perceptual quality values across the compression settings on the compression quality scale. Additionally, the disclosed system then performs a search over the predicted perceptual quality values for the compression settings along the compression quality scale to select a compression setting based on a perceptual quality threshold. The disclosed system generates a compressed digital image according to compression parameters for the selected compression setting.
-
公开(公告)号：US20220101564A1
公开(公告)日：2022-03-31
申请号：US17032704
申请日：2020-09-25
Applicant: Adobe Inc.
Inventor： Meet Patel , Mayur Hemani , Karanjeet Singh , Amit Gupta , Apoorva Gupta , Balaji Krishnamurthy
Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing deep learning to intelligently determine compression settings for compressing a digital image. For instance, the disclosed system utilizes a neural network to generate predicted perceptual quality values for compression settings on a compression quality scale. The disclosed system fits the predicted compression distortions to a perceptual distortion characteristic curve for interpolating predicted perceptual quality values across the compression settings on the compression quality scale. Additionally, the disclosed system then performs a search over the predicted perceptual quality values for the compression settings along the compression quality scale to select a compression setting based on a perceptual quality threshold. The disclosed system generates a compressed digital image according to compression parameters for the selected compression setting.
-
-
-
-
-
-
-
-
-
Search Results
125
records
(took 0.023 seconds)
