-
公开(公告)号：US20210012240A1
公开(公告)日：2021-01-14
申请号：US16902611
申请日：2020-06-16
申请人： Takuya Tanaka , Ryosuke Kasahara , Akira Kinoshita
发明人： Takuya Tanaka , Ryosuke Kasahara , Akira Kinoshita
IPC分类号： G06N20/00
摘要： A learning device includes a learning unit configured to learn a model using learning data stored in a data storage unit; a subsampling unit configured to determine whether to use the learning data corresponding to gradient information updated by an update unit based on the model, for learning of a next model after learning of one model based on a subsampling rate; first and second buffer unit configured to buffer learning data determined to be used for and data determined not to be used for learning of the next model and gradient information corresponding to the learning data, respectively, up to a volume determined in advance. The first buffer unit and the second buffer unit are configured to write the learning data and the gradient information into the data storage unit for each predetermined block when buffering the learning data and the gradient information up to the volume.
-
公开(公告)号：US20200065707A1
公开(公告)日：2020-02-27
申请号：US16545245
申请日：2019-08-20
申请人： Ryosuke KASAHARA , Takuya Tanaka
发明人： Ryosuke KASAHARA , Takuya Tanaka
摘要： A learning device includes: a learning unit configured to read out feature amounts of learning data from a data memory and derive a branch condition for a node of a decision tree based on the feature amounts, to perform learning of the decision tree; and a discriminator configured to perform determining, in accordance with the branch condition, a node to which learning data is to be branched from the node corresponding to the branch condition. The learning unit is configured to, in parallel with processing of the discriminator reading out learning data at a specific node from the data memory via a first port of the data memory and performing the determining, read out, from the data memory via a second port, learning data at a node on which the discriminator is configured to perform determining subsequent to the specific node and derive the branch
-
公开(公告)号：US20190287023A1
公开(公告)日：2019-09-19
申请号：US16294963
申请日：2019-03-07
申请人： Ryosuke Kasahara , Takuya Tanaka
发明人： Ryosuke Kasahara , Takuya Tanaka
摘要： A learning classification device includes a data memory, a learning unit, and a classification unit. The data memory is configured to store training data for learning a decision tree. The learning unit is configured to read a plurality of feature quantities included in the training data from the data memory by single access and derive data of a node based on the plurality of feature quantities, to learn the decision tree. The classification unit is configured to determine where the training data read from the data memory is to be split to from the node, based on the data of the node derived by the learning unit.
-
公开(公告)号：US20180204316A1
公开(公告)日：2018-07-19
申请号：US15872257
申请日：2018-01-16
申请人： Ryosuke KASAHARA , Takuya Tanaka
发明人： Ryosuke KASAHARA , Takuya Tanaka
CPC分类号： G06T7/0002 , G06K9/56 , G06K9/6256 , G06T5/20 , G06T2207/20076 , G06T2207/30168
摘要： An apparatus and a method are disclosed, each of which applies a plurality of different spatial filters to one input image to generate a plurality of filtered images; calculates, for each of a plurality of pixels included in each of the plurality of filtered image, a score indicating a value determined by a difference from a corresponding one of a plurality of model groups, using the plurality of model groups that respectively correspond to the plurality of filtered images and each including one or more models having a parameter representing a target shape; calculates an integrated score indicating a result of integrating the scores of the respective plurality of pixels corresponding to each other over the plurality of filtered images; and determines an abnormality based on the integrated score.
-
公开(公告)号：US10572993B2
公开(公告)日：2020-02-25
申请号：US15873070
申请日：2018-01-17
申请人： Takuya Tanaka , Ryosuke Kasahara
发明人： Takuya Tanaka , Ryosuke Kasahara
摘要： An information processing apparatus and method are disclosed, each of which: using a set of normal data, learns a first model for determining the normal data; sets, out of a plurality of abnormality candidate areas, the abnormality candidate areas selected by a user as correct data and the abnormality candidate areas not selected by the user as incorrect data, to learn a second model for identifying the correct data and the incorrect data, each abnormality candidate area indicating a candidate area of an abnormality and detected based on the first model from each of a plurality of captured images; obtains the captured images; detects the abnormality candidate areas from the respective captured images, using the first model; determines whether the abnormality candidate areas detected belong to the correct data or the incorrect data, using the second model; and controls to output a determination.
-
公开(公告)号：US20200050933A1
公开(公告)日：2020-02-13
申请号：US16529121
申请日：2019-08-01
申请人： Takuya Tanaka , Ryosuke Kasahara
发明人： Takuya Tanaka , Ryosuke Kasahara
摘要： A learning device is configured to perform learning of a decision tree, and includes: a plurality of learning units each corresponding to a data memory of a plurality of data memories, and being configured to perform learning at a first node using learning data acquired by using first addresses related to a storage destination of the learning data corresponding to the first node of the decision tree in the data memory, and output a second address related to a storage destination of each piece of the learning data branched from the first node; and a plurality of managers each corresponding to a learning unit of the plurality of learning units, and being configured to calculate third addresses related to storage destinations of learning data corresponding to second nodes being next nodes of the first node using the first addresses and the second address output from the learning unit.
-
公开(公告)号：US10685432B2
公开(公告)日：2020-06-16
申请号：US15872257
申请日：2018-01-16
申请人： Ryosuke Kasahara , Takuya Tanaka
发明人： Ryosuke Kasahara , Takuya Tanaka
摘要： An apparatus and a method are disclosed, each of which applies a plurality of different spatial filters to one input image to generate a plurality of filtered images; calculates, for each of a plurality of pixels included in each of the plurality of filtered image, a score indicating a value determined by a difference from a corresponding one of a plurality of model groups, using the plurality of model groups that respectively correspond to the plurality of filtered images and each including one or more models having a parameter representing a target shape; calculates an integrated score indicating a result of integrating the scores of the respective plurality of pixels corresponding to each other over the plurality of filtered images; and determines an abnormality based on the integrated score.
-
公开(公告)号：US20200050970A1
公开(公告)日：2020-02-13
申请号：US16527755
申请日：2019-07-31
申请人： Takuya Tanaka , Ryosuke Kasahara
发明人： Takuya Tanaka , Ryosuke Kasahara
摘要： A learning device is configured to perform learning of a decision tree. The learning device includes a gradient output unit and a branch score calculator. The gradient output unit is configured to output a cumulative sum of gradient information corresponding to each value of a feature amount of learning data. The branch score calculator is configured to calculate a branch score used for determining a branch condition for a node of the decision tree, from the cumulative sum without using a dividing circuit.
-
公开(公告)号：US10043090B2
公开(公告)日：2018-08-07
申请号：US15365244
申请日：2016-11-30
申请人： Takuya Tanaka , Ryosuke Kasahara
发明人： Takuya Tanaka , Ryosuke Kasahara
摘要： An information processing device inspects a target image that contains an image of an inspection target. The information processing device includes a pre-processor, a first calculator, a second calculator, and a determiner. The pre-processor is configured to perform pre-processing for comparing the target image with a reference image or a plurality of reference images. The first calculator is configured to define, in the target image, a region of interest (ROI) and surrounding regions that are adjacent to the ROI, and calculate a feature value of the ROI. The second calculator is configured to calculate an outlier from comparison with feature values of images corresponding to the ROI and the surrounding regions in the reference images. The outlier numerically indicates singularity of an image at the ROI. The determiner is configured to provide, based on the outlier, an indicator to be used for the inspection.
-
公开(公告)号：US08646998B2
公开(公告)日：2014-02-11
申请号：US13448546
申请日：2012-04-17
申请人： Takuya Tanaka
发明人： Takuya Tanaka
IPC分类号： B65H75/00
CPC分类号： B41J15/02 , B65H75/245
摘要： A core holding structure includes a shaft portion in which a core for winding thereon a strip-shaped material is inserted and by which the core is rotationally driven. A roller is provided on an outer circumferential surface of the shaft portion. The roller is configured to make contact with an inner circumferential surface of the core inserted in the shaft portion and rotate in a direction in which the core is attached to or detached from the shaft portion. The core holding structure further includes an elastic member configured to hold the roller and bias the roller radially outwards from the shaft portion when pressed toward the surface of the shaft portion.
摘要翻译： 芯保持结构包括轴部分，其中插入有用于卷绕其上的条形材料的芯，并且芯被旋转地驱动。 辊轴设置在轴部的外周面上。 辊构造成与插入在轴部中的芯的内周表面接触并且沿着芯附接到轴部或从轴部分离的方向旋转。 芯保持结构还包括弹性构件，其构造成当辊被朝向轴部的表面受压时，保持辊并将轴径向向外偏压。
-
-
-
-
-
-
-
-
-
搜索结果
42 条记录 (耗时 0.023 秒)
