公开(公告)号：US20230078284A1

公开(公告)日：2023-03-16

申请号：US17944843

申请日：2022-09-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Efthymia TSAMOURA ,  Jaehun LEE ,  Timothy HOSPEDALES

IPC: G06N7/00 ,  G06N5/02

Abstract: Broadly speaking, the present techniques relate to methods and systems for executing a probabilistic program based on an uncertain knowledge base (KB). The methods and systems construct a trigger graph from the uncertain KB, each node of the trigger graph being associated with a rule of the uncertain KB.

公开(公告)号：US20240232587A1

公开(公告)日：2024-07-11

申请号：US18429690

申请日：2024-02-01

Applicant: Samsung Electronics Co., Ltd.

Inventor： Srinivas Soumitri MIRIYALA ,  Efthymia TSAMOURA ,  Shah Ayub QUADRI ,  Vikram Nelvoy RAJENDIRAN ,  Venkappa MALA

IPC: G06N3/047 ,  G06N7/01

CPC classification number: G06N3/047 ,  G06N7/01

Abstract: A method and an electronic device for neuro-symbolic learning of an artificial intelligence (AI) model are provided. The method includes receiving input data including various contents and determining in an output of the AI model a predicted probability for each of the contents of the input data, determining a neural loss of the AI model by comparing the predicted probability with a predefined desired probability, determining a symbolic loss for the AI model by comparing the predicted probability with a pre-determined undesired probability, determining weights of a plurality of layers of the AI model, and updating the weights of the plurality of layers of the AI model based on the neural loss and the symbolic loss.

公开(公告)号：US20220391704A1

公开(公告)日：2022-12-08

申请号：US17824571

申请日：2022-05-25

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Efthymia TSAMOURA ,  Davide BUFFELLI

IPC: G06N3/08 ,  G06N3/04 ,  G06V10/75 ,  G06V10/771 ,  G06V10/774 ,  G06V10/82 ,  G06V10/84

Abstract: Broadly speaking, the disclosure generally relates to relates to a computer-implemented methods and systems for scene graph generation, and in particular for training a machine learning, ML, model to generate a scene graph. The method includes inputting training a training image into a machine learning model, outputting a predicted label for at least two objects in the training image and a predicted label for a relationship between the at least two objects. The training method includes calculating a loss, which takes into account both a supervised loss calculated by comparing the predicted labels to the actual labels for the training image, and a logic-based loss calculated by comparing the predicted labels to stored integrity constraints comprising common-sense knowledge. Advantageously, this means that the performance of the model is improved without increasing processing at inference-time.