知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

7 records (took 0.015 seconds)

    Context aware text-to-image synthesis
    2.
    发明授权
    Context aware text-to-image synthesis 有权

    公开(公告)号：US10713821B1

    公开(公告)日：2020-07-14

    申请号：US16454829

    申请日：2019-06-27

    Applicant: Amazon Technologies, Inc.

    Inventor： Shiv Surya ,  Arijit Biswas ,  Sumit Negi ,  Amrith Rajagopal Setlur

    IPC: G06N3/08 ,  G06T11/00 ,  G06T11/20 ,  G06F40/30

    Abstract: Techniques are generally described for context aware text-to-image synthesis. First text data comprising a description of an object may be received. A recurrent neural network may determine a first semantic representation data representing the first text data. A generator trained using a first generative adversarial network (GAN) may determine first image data representing the object using the first semantic representation. An encoder of a second GAN may generate a first feature representation of the first image data. The first feature representation may be combined with a projection of the first semantic representation data. A decoder of the second GAN may generate second image data representing the first text data.

    Low-dimensional neural-network-based entity representation
    3.
    发明授权
    Low-dimensional neural-network-based entity representation 有权

    公开(公告)号：US11941517B1

    公开(公告)日：2024-03-26

    申请号：US15821660

    申请日：2017-11-22

    Applicant: Amazon Technologies, Inc.

    Inventor： Arijit Biswas ,  Subhajit Sanyal

    IPC: G06N3/08

    CPC classification number: G06N3/08

    Abstract: Systems and methods are disclosed to implement a neural network training system to train a multitask neural network (MNN) to generate a low-dimensional entity representation based on a sequence of events associated with the entity. In embodiments, an encoder is combined with a group of decoders to form a MNN to perform different machine learning tasks on entities. During training, the encoder takes a sequence of events in and generates a low-dimensional representation of the entity. The decoders then take the representation and perform different tasks to predict various attributes of the entity. As the MNN is trained to perform the different tasks, the encoder is also trained to generate entity representations that capture different attribute signals of the entities. The trained encoder may then be used to generate semantically meaningful entity representations for use with other machine learning systems.

    LOW-DIMENSIONAL NEURAL-NETWORK-BASED ENTITY REPRESENTATION
    5.
    发明公开
    LOW-DIMENSIONAL NEURAL-NETWORK-BASED ENTITY REPRESENTATION 审中-公开

    公开(公告)号：US20240193420A1

    公开(公告)日：2024-06-13

    申请号：US18587662

    申请日：2024-02-26

    Applicant: Amazon Technologies, Inc.

    Inventor： Arijit Biswas ,  Subhajit Sanyal

    IPC: G06N3/08

    CPC classification number: G06N3/08

    Abstract: Systems and methods are disclosed to implement a neural network training system to train a multitask neural network (MNN) to generate a low-dimensional entity representation based on a sequence of events associated with the entity. In embodiments, an encoder is combined with a group of decoders to form a MNN to perform different machine learning tasks on entities. During training, the encoder takes a sequence of events in and generates a low-dimensional representation of the entity. The decoders then take the representation and perform different tasks to predict various attributes of the entity. As the MNN is trained to perform the different tasks, the encoder is also trained to generate entity representations that capture different attribute signals of the entities. The trained encoder may then be used to generate semantically meaningful entity representations for use with other machine learning systems.

    NATURAL LANGUAGE GENERATION
    6.
    发明申请
    NATURAL LANGUAGE GENERATION 有权

    公开(公告)号：US20250006196A1

    公开(公告)日：2025-01-02

    申请号：US18345455

    申请日：2023-06-30

    Applicant: Amazon Technologies, Inc.

    Inventor： Hann Wang ,  Angeliki Metallinou ,  Melanie C B Gens ,  Arijit Biswas ,  Ying Shi

    IPC: G10L15/26 ,  G10L13/08

    Abstract: Techniques for generating a prompt for a language model to determine an action responsive to a user input, are described. In some embodiments, the system receives a user input, determines one or more application programming interfaces (APIs) configured to perform actions that are relevant to the user input and exemplars representing examples of using the APIs with respect to user inputs similar to the current user input. The system further determines device states of devices that are determined to be related to the user input and also determines other contextual information (e.g., weather information, time of day, geographic location, etc.). The system generates a prompt including the user input, the APIs, the exemplars, the device states, and the other contextual information. A language model processes the prompt to determine an action responsive to the user input and the system causes performance of the action.

Patent Agency Ranking