公开(公告)号：US20210117718A1

公开(公告)日：2021-04-22

申请号：US16659147

申请日：2019-10-21

Applicant: Adobe Inc.

Inventor： Pinkesh Badjatiya ,  Nikaash Puri ,  Ayush Chopra ,  Anubha Kabra

IPC: G06K9/62 ,  G06N20/10

Abstract: A data classification system is trained to classify input data into multiple classes. The system is initially trained by adjusting weights within the system based on a set of training data that includes multiple tuples, each being a training instance and corresponding training label. Two training instances, one from a minority class and one from a majority class, are selected from the set of training data based on entropies for the training instances. A synthetic training instance is generated by combining the two selected training instances and a corresponding training label is generated. A tuple including the synthetic training instance and the synthetic training label is added to the set of training data, resulting in an augmented training data set. One or more such synthetic training instances can be added to the augmented training data set and the system is then re-trained on the augmented training data set.

公开(公告)号：US11907816B2

公开(公告)日：2024-02-20

申请号：US17892878

申请日：2022-08-22

Applicant: Adobe Inc.

Inventor： Pinkesh Badjatiya ,  Nikaash Puri ,  Ayush Chopra ,  Anubha Kabra

IPC: G06N20/00 ,  G06N20/10 ,  G06F18/2431 ,  G06F18/211 ,  G06F18/214 ,  G06F18/2453

CPC classification number: G06N20/00 ,  G06F18/211 ,  G06F18/214 ,  G06F18/2431 ,  G06F18/2453 ,  G06N20/10

Abstract: A data classification system is trained to classify input data into multiple classes. The system is initially trained by adjusting weights within the system based on a set of training data that includes multiple tuples, each being a training instance and corresponding training label. Two training instances, one from a minority class and one from a majority class, are selected from the set of training data based on entropies for the training instances. A synthetic training instance is generated by combining the two selected training instances and a corresponding training label is generated. A tuple including the synthetic training instance and the synthetic training label is added to the set of training data, resulting in an augmented training data set. One or more such synthetic training instances can be added to the augmented training data set and the system is then re-trained on the augmented training data set.

公开(公告)号：US20230196191A1

公开(公告)日：2023-06-22

申请号：US17892878

申请日：2022-08-22

Applicant: Adobe Inc.

Inventor： Pinkesh Badjatiya ,  Nikaash Puri ,  Ayush Chopra ,  Anubha Kabra

IPC: G06N20/00 ,  G06N20/10 ,  G06F18/2431 ,  G06F18/211 ,  G06F18/214 ,  G06F18/2453

CPC classification number: G06N20/00 ,  G06N20/10 ,  G06F18/2431 ,  G06F18/211 ,  G06F18/214 ,  G06F18/2453

Abstract: A data classification system is trained to classify input data into multiple classes. The system is initially trained by adjusting weights within the system based on a set of training data that includes multiple tuples, each being a training instance and corresponding training label. Two training instances, one from a minority class and one from a majority class, are selected from the set of training data based on entropies for the training instances. A synthetic training instance is generated by combining the two selected training instances and a corresponding training label is generated. A tuple including the synthetic training instance and the synthetic training label is added to the set of training data, resulting in an augmented training data set. One or more such synthetic training instances can be added to the augmented training data set and the system is then re-trained on the augmented training data set.

公开(公告)号：US11423264B2

公开(公告)日：2022-08-23

申请号：US16659147

申请日：2019-10-21

Applicant: Adobe Inc.

Inventor： Pinkesh Badjatiya ,  Nikaash Puri ,  Ayush Chopra ,  Anubha Kabra

IPC: G06K9/62 ,  G06N20/10

Abstract: A data classification system is trained to classify input data into multiple classes. The system is initially trained by adjusting weights within the system based on a set of training data that includes multiple tuples, each being a training instance and corresponding training label. Two training instances, one from a minority class and one from a majority class, are selected from the set of training data based on entropies for the training instances. A synthetic training instance is generated by combining the two selected training instances and a corresponding training label is generated. A tuple including the synthetic training instance and the synthetic training label is added to the set of training data, resulting in an augmented training data set. One or more such synthetic training instances can be added to the augmented training data set and the system is then re-trained on the augmented training data set.