知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.017 seconds)

    INFORMATION PROCESSING APPARATUS AND INFORMATION PROCESSING METHOD
    2.
    发明申请
    INFORMATION PROCESSING APPARATUS AND INFORMATION PROCESSING METHOD 审中-公开

    公开(公告)号：US20190050713A1

    公开(公告)日：2019-02-14

    申请号：US16076851

    申请日：2017-01-24

    Applicant: SONY CORPORATION

    Inventor： Takuya NARIHIRA ,  Takuya FUJITA ,  Akira NAKAMURA

    IPC: G06N3/04 ,  G06N3/08

    Abstract: There is provided an information processing apparatus that can perform learning of a neural network more efficiently, the information processing apparatus including: an acquisition section configured to acquire a semantic network, identification information of data, and a label; and a learning section configured to learn a classification model that classifies the data into the label, on a basis of the semantic network, the identification information, and the label that have been acquired by the acquisition section.

    INFORMATION PROCESSING DEVICE
    3.
    发明申请
    INFORMATION PROCESSING DEVICE 审中-公开

    公开(公告)号：US20180082178A1

    公开(公告)日：2018-03-22

    申请号：US15566327

    申请日：2016-12-27

    Applicant: SONY CORPORATION

    Inventor： Akira NAKAMURA ,  Takuya NARIHIRA ,  Takuya FUJITA

    IPC: G06N3/08 ,  G06F17/50 ,  G06T3/40 ,  G06T17/05 ,  G01V99/00

    Abstract: There is provided an information processing device to improve generalization performance of the neural network, the information processing device including: a control unit configured to control display related to a setting of a parameter related to physical simulation; a communication unit configured to transmit the parameter to a physical simulator and receive image information obtained in the physical simulation from the physical simulator; and a machine learning unit configured to perform machine learning on the basis of the image information. The control unit causes a display unit to display a learning result obtained by the machine learning unit and the parameter in association with each other.

    INFORMATION PROCESSING APPARATUS, AND INFORMATION PROCESSING METHOD, AND PROGRAM
    4.
    发明申请
    INFORMATION PROCESSING APPARATUS, AND INFORMATION PROCESSING METHOD, AND PROGRAM 审中-公开

    公开(公告)号：US20190332951A1

    公开(公告)日：2019-10-31

    申请号：US16475540

    申请日：2017-11-09

    Applicant: SONY CORPORATION

    Inventor： Ryo NAKAHASHI ,  Hirotaka SUZUKI ,  Takuya NARIHIRA ,  Atsushi NODA

    IPC: G06N5/02 ,  G06F16/906 ,  A63F13/46

    Abstract: Provided are an apparatus and a method enabling efficient reinforcement learning to be performed by input of an annotation. Included are a database configured to store respective pieces of information of a state, an action, and a reward of a processing execution unit, a learning execution unit configured to execute learning processing in accordance with a reinforcement learning algorithm to which the information stored in the database is applied, and an annotation input unit configured to input annotation information including sub reward setting information and store the annotation information in the database. The learning execution unit executes learning processing to which the respective pieces of information of the state, the action, and the reward input from the processing execution unit and the sub reward setting information are applied, derives an action determination rule, and determines an action which is caused to be executed in accordance with the action determination rule.

    INFORMATION PROCESSING UNIT, INFORMATION PROCESSING METHOD, AND PROGRAM
    6.
    发明申请
    INFORMATION PROCESSING UNIT, INFORMATION PROCESSING METHOD, AND PROGRAM 有权
    信息处理单元，信息处理方法和程序

    公开(公告)号：US20150347505A1

    公开(公告)日：2015-12-03

    申请号：US14652581

    申请日：2013-12-06

    Applicant: SONY CORPORATION ,  JAPANESE FOUNDATION FOR CANCER RESEARCH

    Inventor： Takeshi OHASHI ,  Jun YOKONO ,  Takuya NARIHIRA

    IPC: G06F17/30 ,  G06K9/62 ,  G06T7/00

    CPC classification number: G06F17/30424 ,  G06F17/30247 ,  G06F17/30265 ,  G06F17/30277 ,  G06F17/3028 ,  G06F19/00 ,  G06F19/321 ,  G06K9/00147 ,  G06K9/6215 ,  G06K9/6253 ,  G06Q50/24 ,  G06T7/0012 ,  G06T2200/24 ,  G06T2207/30024 ,  G06T2207/30096

    Abstract: An information processing unit includes: a diagnostic image input section that inputs the diagnostic image; an operation information obtaining section that obtains display operation history information representing an operation history of a user who controls displaying of the diagnostic image; a query image generation section that extracts a predetermined region of the input diagnostic image to generate a query image; a diagnosed image obtaining section that supplies the generated query image and the display operation history information to a diagnosed image search unit and obtains the diagnosed image obtained as a search result by the diagnosed image search unit; and a display control section that displays the diagnostic image and the obtained diagnosed image for comparison.

    Abstract translation: 信息处理单元包括：诊断图像输入部，其输入诊断图像; 操作信息获取部，其获取表示控制诊断图像的显示的用户的操作历史的显示操作历史信息; 查询图像生成部，其提取输入诊断图像的规定区域，生成查询图像; 诊断图像获取部分，其将生成的查询图像和显示操作历史信息提供给诊断图像搜索单元，并获得由诊断图像搜索单元获得的诊断图像作为搜索结果; 以及显示控制部，显示诊断图像和所获得的诊断图像进行比较。

    INFORMATION PROCESSING APPARATUS AND INFORMATION PROCESSING METHOD
    8.
    发明申请
    INFORMATION PROCESSING APPARATUS AND INFORMATION PROCESSING METHOD 审中-公开

    公开(公告)号：US20190272558A1

    公开(公告)日：2019-09-05

    申请号：US16343644

    申请日：2017-11-30

    Applicant: SONY CORPORATION

    Inventor： Hirotaka SUZUKI ,  Takuya NARIHIRA ,  Akihito OSATO ,  Kento NAKADA

    IPC: G06Q30/02 ,  G06F17/50 ,  G06N5/02

    Abstract: There is provided an information processing apparatus and an information processing method allowing variations of scenes of various events to be realized in a simulator environment simulating the real world. A reward providing unit provides rewards to a first agent and a second agent taking action in the simulator environment and learning an action decision rule according to the reward for the action. The first agent is provided with the reward in accordance with a prescribed reward definition. The second agent is provided with the reward in accordance with an opposing reward definition opposing the prescribed reward definition, the opposing reward definition causing a resultant reward to be increased in a case where the second agent acts to bring about a situation where the reward for the first agent is reduced and causing a resultant reward to be reduced in a case the reward for the first agent is increased.

    LEARNING APPARATUS AND LEARNING METHOD
    9.
    发明申请
    LEARNING APPARATUS AND LEARNING METHOD 审中-公开

    公开(公告)号：US20190244133A1

    公开(公告)日：2019-08-08

    申请号：US16343940

    申请日：2017-12-14

    Applicant: SONY CORPORATION

    Inventor： Kento NAKADA ,  Takuya NARIHIRA ,  Hirotaka SUZUKI ,  Akihito OSATO

    IPC: G06N20/00 ,  G09G5/00

    CPC classification number: G06N20/00 ,  G06N99/00 ,  G09G5/003

    Abstract: There is provided a learning apparatus and a learning method that allow a reinforcement learning model to be easily corrected on the basis of user input. A display control section causes a display section to display reinforcement learning model information regarding a reinforcement learning model. A correcting section corrects the reinforcement learning model on the basis of user input to the reinforcement learning model information. The present disclosure can be applied to, for example, a personal computer (PC) and the like that correct a reinforcement learning model on the basis of input from a user and perform reinforcement learning of a movement policy of an agent using the corrected reinforcement learning model.

Patent Agency Ranking