知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

28 条记录 (耗时 0.017 秒)

    USING CORRECTIONS, OF AUTOMATED ASSISTANT FUNCTIONS, FOR TRAINING OF ON-DEVICE MACHINE LEARNING MODELS
    1.
    发明公开
    USING CORRECTIONS, OF AUTOMATED ASSISTANT FUNCTIONS, FOR TRAINING OF ON-DEVICE MACHINE LEARNING MODELS 审中-公开

    公开(公告)号：US20240296843A1

    公开(公告)日：2024-09-05

    申请号：US18657405

    申请日：2024-05-07

    申请人： GOOGLE LLC

    发明人： Françoise Beaufays ,  Rajiv Mathews ,  Dragan Zivkovic ,  Kurt Partridge ,  Andrew Hard

    IPC分类号： G10L15/22 ,  G10L15/065 ,  G10L15/10 ,  G10L15/30

    CPC分类号： G10L15/22 ,  G10L15/065 ,  G10L15/10 ,  G10L15/30

    摘要： Processor(s) of a client device can: receive sensor data that captures environmental attributes of an environment of the client device; process the sensor data using a machine learning model to generate a predicted output that dictates whether one or more currently dormant automated assistant functions are activated; making a decision as to whether to trigger the one or more currently dormant automated assistant functions; subsequent to making the decision, determining that the decision was incorrect; and in response to determining that the determination was incorrect, generating a gradient based on comparing the predicted output to ground truth output. In some implementations, the generated gradient is used, by processor(s) of the client device, to update weights of the on-device speech recognition model. In some implementations, the generated gradient is additionally or alternatively transmitted to a remote system for use in remote updating of global weights of a global speech recognition model.

    USING CORRECTIONS, OF AUTOMATED ASSISTANT FUNCTIONS, FOR TRAINING OF ON-DEVICE MACHINE LEARNING MODELS
    3.
    发明申请
    USING CORRECTIONS, OF AUTOMATED ASSISTANT FUNCTIONS, FOR TRAINING OF ON-DEVICE MACHINE LEARNING MODELS 有权

    公开(公告)号：US20210327421A1

    公开(公告)日：2021-10-21

    申请号：US16973572

    申请日：2019-11-08

    申请人： Google LLC

    发明人： Françoise Beaufays ,  Rajiv Mathews ,  Dragan Zivkovic ,  Kurt Partridge ,  Andrew Hard

    IPC分类号： G10L15/22 ,  G10L15/065 ,  G10L15/10 ,  G10L15/30

    摘要： Processor(s) of a client device can: receive sensor data that captures environmental attributes of an environment of the client device; process the sensor data using a machine learning model to generate a predicted output that dictates whether one or more currently dormant automated assistant functions are activated; making a decision as to whether to trigger the one or more currently dormant automated assistant functions; subsequent to making the decision, determining that the decision was incorrect; and in response to determining that the determination was incorrect, generating a gradient based on comparing the predicted output to ground truth output. In some implementations, the generated gradient is used, by processor(s) of the client device, to update weights of the on-device speech recognition model. In some implementations, the generated gradient is additionally or alternatively transmitted to a remote system for use in remote updating of global weights of a global speech recognition model.

    Phrase extraction for ASR models
    4.
    发明授权
    Phrase extraction for ASR models 有权

    公开(公告)号：US11955134B2

    公开(公告)日：2024-04-09

    申请号：US17643848

    申请日：2021-12-13

    申请人： Google LLC

    发明人： Ehsan Amid ,  Om Thakkar ,  Rajiv Mathews ,  Francoise Beaufays

    IPC分类号： G10L21/0332 ,  G10L15/06 ,  G10L15/08 ,  G10L21/10

    CPC分类号： G10L21/0332 ,  G10L15/063 ,  G10L15/08 ,  G10L21/10

    摘要： A method of phrase extraction for ASR models includes obtaining audio data characterizing an utterance and a corresponding ground-truth transcription of the utterance and modifying the audio data to obfuscate a particular phrase recited in the utterance. The method also includes processing, using a trained ASR model, the modified audio data to generate a predicted transcription of the utterance, and determining whether the predicted transcription includes the particular phrase by comparing the predicted transcription of the utterance to the ground-truth transcription of the utterance. When the predicted transcription includes the particular phrase, the method includes generating an output indicating that the trained ASR model leaked the particular phrase from a training data set used to train the ASR model.

    USING CORRECTIONS, OF AUTOMATED ASSISTANT FUNCTIONS, FOR TRAINING OF ON-DEVICE MACHINE LEARNING MODELS
    6.
    发明公开
    USING CORRECTIONS, OF AUTOMATED ASSISTANT FUNCTIONS, FOR TRAINING OF ON-DEVICE MACHINE LEARNING MODELS 审中-公开

    公开(公告)号：US20230352019A1

    公开(公告)日：2023-11-02

    申请号：US18218818

    申请日：2023-07-06

    申请人： GOOGLE LLC

    发明人： Françoise Beaufays ,  Rajiv Mathews ,  Dragan Zivkovic ,  Kurt Partridge ,  Andrew Hard

    IPC分类号： G10L15/22 ,  G10L15/065 ,  G10L15/10 ,  G10L15/30

    CPC分类号： G10L15/22 ,  G10L15/065 ,  G10L15/10 ,  G10L15/30

    摘要： Processor(s) of a client device can: receive sensor data that captures environmental attributes of an environment of the client device; process the sensor data using a machine learning model to generate a predicted output that dictates whether one or more currently dormant automated assistant functions are activated; making a decision as to whether to trigger the one or more currently dormant automated assistant functions; subsequent to making the decision, determining that the decision was incorrect; and in response to determining that the determination was incorrect, generating a gradient based on comparing the predicted output to ground truth output. In some implementations, the generated gradient is used, by processor(s) of the client device, to update weights of the on-device speech recognition model. In some implementations, the generated gradient is additionally or alternatively transmitted to a remote system for use in remote updating of global weights of a global speech recognition model.

    MIXED CLIENT-SERVER FEDERATED LEARNING OF MACHINE LEARNING MODEL(S)
    7.
    发明公开
    MIXED CLIENT-SERVER FEDERATED LEARNING OF MACHINE LEARNING MODEL(S) 审中-公开

    公开(公告)号：US20230352004A1

    公开(公告)日：2023-11-02

    申请号：US18218319

    申请日：2023-07-05

    申请人： GOOGLE LLC

    发明人： Françoise Beaufays ,  Andrew Hard ,  Swaroop Indra Ramaswamy ,  Om Dipakbhai Thakkar ,  Rajiv Mathews

    IPC分类号： G10L15/065 ,  G10L13/04 ,  G10L15/26 ,  G10L15/30

    CPC分类号： G10L15/065 ,  G10L13/04 ,  G10L15/26 ,  G10L15/30

    摘要： Implementations disclosed herein are directed to federated learning of machine learning (“ML”) model(s) based on gradient(s) generated at corresponding client devices and a remote system. Processor(s) of the corresponding client devices can process client data generated locally at the corresponding client devices using corresponding on-device ML model(s) to generate corresponding predicted outputs, generate corresponding client gradients based on the corresponding predicted outputs, and transmit the corresponding client gradients to the remote system. Processor(s) of the remote system can process remote data obtained from remote database(s) using global ML model(s) to generate additional corresponding predicted outputs, generate corresponding remote gradients based on the additional corresponding predicted outputs. Further, the remote system can utilize the corresponding client gradients and the corresponding remote gradients to update the global ML model(s) or weights thereof. The updated global ML model(s) and/or the updated weights thereof can be transmitted back to the corresponding client devices.

    CO-DISTILLATION FOR MIXING SERVER-BASED AND FEDERATED LEARNING
    9.
    发明公开
    CO-DISTILLATION FOR MIXING SERVER-BASED AND FEDERATED LEARNING 审中-公开

    公开(公告)号：US20240330767A1

    公开(公告)日：2024-10-03

    申请号：US18611628

    申请日：2024-03-20

    申请人： Google LLC

    发明人： Andrew Hard ,  Rajiv Mathews

    IPC分类号： G06N20/00

    CPC分类号： G06N20/00

    摘要： A method includes training a client machine learning (ML) model on client training data at a client device. While training the client ML model, the method also includes obtaining, from a server, server model weights of a server ML model trained on server training data, the server training data different that the client training data. While training the client ML model, the method also includes: transmitting, to the server, client model weights of the client ML model; updating the client ML model using the server model weights; obtaining, from the server, updated server model weights of the server ML model, the updated server model weights updated based on the transmitted client model weights; and further updating the client ML model using the updated server model weights.

    SYSTEM(S) AND METHOD(S) TO REDUCE A TRANSFERABLE SIZE OF LANGUAGE MODEL(S) TO ENABLE DECENTRALIZED LEARNING THEREOF
    10.
    发明公开
    SYSTEM(S) AND METHOD(S) TO REDUCE A TRANSFERABLE SIZE OF LANGUAGE MODEL(S) TO ENABLE DECENTRALIZED LEARNING THEREOF 审中-公开

    公开(公告)号：US20240265269A1

    公开(公告)日：2024-08-08

    申请号：US18125613

    申请日：2023-03-23

    申请人： GOOGLE LLC

    发明人： Mingqing Chen ,  Lara McConnaughey ,  Kaan Ege Özgün ,  Rajiv Mathews ,  Françoise Beaufays

    IPC分类号： G06N3/098 ,  G06F40/40 ,  G06N3/044

    CPC分类号： G06N3/098 ,  G06F40/40 ,  G06N3/044

    摘要： Implementations disclosed herein are directed to techniques for enabling decentralized learning of global language models (LMs). Remote processor(s) of a remote system can obtain a global LM that includes a global embedding matrix, generate a global embedding mask for the global embedding matrix using a masking technique, apply the global embedding mask to global embedding matrix to generate a sparsified global LM that includes a masked global embedding matrix that is a masked version of the global embedding matrix, transmit the sparsified global LM to computing device(s) that are participating in a given round of decentralized learning for the global language model, receive corresponding updates from the computing device(s), and cause the global LM to be updated based on the corresponding updates. By generating the global embedding mask and applying it to the global embedding matrix, the transferable size of the global LM is reduced thereby enabling decentralized learning thereof.