中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

42 records (took 0.016 seconds)

    Scalable distributed data processing and indexing
    11.
    发明授权
    Scalable distributed data processing and indexing 有权

    公开(公告)号：US11023440B1

    公开(公告)日：2021-06-01

    申请号：US15634334

    申请日：2017-06-27

    Applicant: Amazon Technologies, Inc.

    Inventor： Pracheer Gupta ,  Madan Mohan Rao Jampani ,  Andrea Olgiati ,  Poorna Chand Srinivas Perumalla ,  Stefano Stefani

    IPC: G06F16/00 ,  G06F16/22 ,  G06F16/901

    Abstract: A computing resource service provider deploys resources to process input data sets on an ongoing basis and provide requestors with queryable data structures generated from the input data sets over determined, rolling periods of time. In one embodiment, the input data sets are processed using one or more nearest neighbor search algorithms, and the outputs therefrom are represented in data structures which are rotated as newer data structures are subsequently generated. The disclosed systems and techniques improve resource utilization, processing efficiency, query latency, and result consistency relative to known controls for large and/or complex data processing tasks, such as those employed in machine learning techniques.

    CONFIDENTIAL TUNING OF PRE-TRAINED MACHINE LEARNING MODELS
    15.
    发明公开
    CONFIDENTIAL TUNING OF PRE-TRAINED MACHINE LEARNING MODELS 审中-公开

    公开(公告)号：US20240177049A1

    公开(公告)日：2024-05-30

    申请号：US18058840

    申请日：2022-11-25

    Applicant: Amazon Technologies, Inc.

    Inventor： Lakshmi Naarayanan Ramakrishnan ,  Andrea Olgiati ,  Ankur Mehrotra ,  Karthik Gurumoorthy Subramanya Bharathy ,  Rakesh Ramakrishnan

    IPC: G06N20/00

    CPC classification number: G06N20/00

    Abstract: Confidential tuning of pre-trained machine learning models may be provided. A request associated with a model user account to fine-tune a pre-trained machine learning model with model access restrictions may be received. The pre-trained machine learning model may be one of many pre-trained machine learning models uploaded for selection and fine-tuning. The pre-trained machine learning model may be further trained using a request specified data set, with the model access restrictions and access restrictions for the data set being enforced as part of the training. Then, the fine-tuned machine learning model may be made available for invocation by an application associated with the model user account without violating the model access restrictions and data access restrictions.

    GPU CODE INJECTION TO SUMMARIZE MACHINE LEARNING TRAINING DATA
    18.
    发明申请
    GPU CODE INJECTION TO SUMMARIZE MACHINE LEARNING TRAINING DATA 有权

    公开(公告)号：US20210097432A1

    公开(公告)日：2021-04-01

    申请号：US16588930

    申请日：2019-09-30

    Applicant: Amazon Technologies, Inc.

    Inventor： Andrea Olgiati ,  Rahul Raghavendra Huilgol ,  Vikas Kumar

    IPC: G06N20/00 ,  G06F17/18 ,  G06T1/20

    Abstract: Methods, systems, and computer-readable media for GPU code injection to summarize machine learning training data are disclosed. Training of a machine learning model is initiated using a graphics processing unit (GPU) associated with a machine learning training cluster. The training of the machine learning model generates tensor data in a memory of the GPU. The GPU determines a summary of the tensor data according to a reduction operator. The summary is smaller in size than the tensor data and is output by the GPU. A machine learning analysis system performs an analysis of the training of the machine learning model based at least in part on the summary of the tensor data. The machine learning analysis system detects one or more conditions associated with the training of the machine learning model based at least in part on the analysis.

    IMPROPER NEURAL NETWORK INPUT DETECTION AND HANDLING
    19.
    发明申请
    IMPROPER NEURAL NETWORK INPUT DETECTION AND HANDLING 审中-公开

    公开(公告)号：US20200184245A1

    公开(公告)日：2020-06-11

    申请号：US16216485

    申请日：2018-12-11

    Applicant: Amazon Technologies, Inc.

    Inventor： Randy Renfu Huang ,  Richard John Heaton ,  Andrea Olgiati ,  Ron Diamant

    IPC: G06K9/03 ,  G06N3/04 ,  G06N3/08 ,  G06K9/62

    Abstract: Systems and methods for performing improper input data detection are described. In one example, a system comprises: hardware circuits configured to receive input data and to perform computations of a neural network based on the input data to generate computation outputs; and an improper input detection circuit configured to: determine a relationship between the computation outputs of the hardware circuits and reference outputs; determine that the input data are improper based on the relationship; and perform an action based on determining that the input data are improper.

    Memory management unit for shared memory allocation
    20.
    发明授权
    Memory management unit for shared memory allocation 有权

    公开(公告)号：US10310986B1

    公开(公告)日：2019-06-04

    申请号：US15826209

    申请日：2017-11-29

    Applicant: Amazon Technologies, Inc.

    Inventor： Andrea Olgiati

    IPC: G06F12/00 ,  G06F12/1009 ,  G06F12/02

    Abstract: A system and method for allocating shared inter-process memory by a memory management unit is disclosed. A memory management unit may receive information indicative of allocating a region of shared memory. The information may further indicate that a second process may share access to the memory. The memory management unit may identify corresponding regions of virtual address space for each process, such that the region in each address space maps to the same range of addresses. The memory management unit may virtualize access to the shared memory by mapping from the corresponding regions of the virtual address space.

Patent Agency Ranking