-
公开(公告)号：EP3514730A1
公开(公告)日：2019-07-24
申请号：EP19151825.7
申请日：2019-01-15
申请人： Hitachi, Ltd.
摘要： Provided is a boundary search test support device (100) to make it possible to detect boundary points at which output values change in a program created by machine learning more efficiently. The boundary search test support device (100) includes: a storage device that holds a plurality of input vectors (1111); and an arithmetic device that executes a test by sequentially inputting the input vectors to a program generated by a neural network and acquiring output vectors (1141) which are test results, respectively generates, in a coordinate system which takes each of a predetermined plurality of elements among elements constituting the output vectors as a coordinate axis, a straight line in which the plurality of elements has a same value and a hyperplane in which a sum of values of the plurality of elements is taken as a predetermined value, and arranges a most antagonistic point and boundary vectors whose values of the elements rank higher than or equal to a predetermined ranking among the output vectors in the coordinate system, and outputs the coordinate system together with input vectors (1111) corresponding to the boundary vectors on a predetermined output device.
-
公开(公告)号：EP4030353A3
公开(公告)日：2022-08-03
申请号：EP21216309.1
申请日：2021-12-21
申请人： Hitachi, Ltd.
发明人： MYOJIN, Tomoyuki , KURUMA, Hironobu , SATO, Naoto , OGAWA, Hideto
摘要： To efficiently verify and improve a robustness of a learning model for supervised machine learning. A data-creation assistance apparatus 100 includes: a storage device 101 configured to store a neural network model 110 and test data 120; and a computing device 104 configured to specify an uncertainty of an inference result acquired by the neural network model 110; acquire gradient information of the test data 120 by a back propagation process using the uncertainty as a loss; apply various minute changes to the test data 120 to generate a plurality of minutely changed test data, and calculate deviations between each of the plurality of pieces minutely changed test data and the test data 120; and specify, based on the uncertainty information, the gradient information, and the deviations, a minute change that increases or decreases the uncertainty.
-
-
公开(公告)号：EP3321808A1
公开(公告)日：2018-05-16
申请号：EP17198379.4
申请日：2017-10-25
申请人： Hitachi, Ltd.
CPC分类号： G06F11/2242 , G06F11/3457 , G06F11/3604 , G06F11/3672
摘要： A verification system comprising a verification center and function management systems, wherein each of the function management systems retains function management information for associating a function of each of information processing systems corresponding to each of the function management systems; a range of parameter values that can be set for the function; a range of parameter values for the functions that have been verified; and actually set parameter values, wherein, if the actually set parameter value is modified to a value outside of the verified range, then prior to the modification, each of the function management systems transmits to the verification center a verification request of the function in which a parameter value in a range including the modified value is set, and wherein the verification center executes verification on the basis of the verification request, and transmits results thereof to the function management system.
摘要翻译： 一种验证系统，包括验证中心和功能管理系统，其中每个功能管理系统保留用于关联与每个功能管理系统相对应的每个信息处理系统的功能的功能管理信息; 可为该功能设置的一系列参数值; 已验证功能的一系列参数值; 并且实际设置参数值，其中，如果实际设置的参数值被修改为在验证的范围之外的值，则在修改之前，每个功能管理系统向验证中心发送功能的验证请求，其中 设置包括修改值的范围中的参数值，并且其中验证中心基于验证请求执行验证，并且将结果发送到功能管理系统。
-
公开(公告)号：EP4030353A2
公开(公告)日：2022-07-20
申请号：EP21216309.1
申请日：2021-12-21
申请人： Hitachi, Ltd.
发明人： MYOJIN, Tomoyuki , KURUMA, Hironobu , SATO, Naoto , OGAWA, Hideto
摘要： To efficiently verify and improve a robustness of a learning model for supervised machine learning. A data-creation assistance apparatus 100 includes: a storage device 101 configured to store a neural network model 110 and test data 120; and a computing device 104 configured to specify an uncertainty of an inference result acquired by the neural network model 110; acquire gradient information of the test data 120 by a back propagation process using the uncertainty as a loss; apply various minute changes to the test data 120 to generate a plurality of minutely changed test data, and calculate deviations between each of the plurality of pieces minutely changed test data and the test data 120; and specify, based on the uncertainty information, the gradient information, and the deviations, a minute change that increases or decreases the uncertainty.
-
公开(公告)号：EP3506104A1
公开(公告)日：2019-07-03
申请号：EP18214895.7
申请日：2018-12-20
申请人： Hitachi, Ltd.
摘要： A coverage test support device includes a memory device that stores a test case and a specification content of each of a plurality of coverage indexes, and an arithmetic device that sequentially gives a test input value of each pair in the test case to a program created by a neural network, executes a predetermined number of tests, and acquires a test result of the tests and neuron information at the time of test execution, applies the acquired neuron information to the specification content of each of the plurality of coverage indexes and calculates a value for each coverage index, and identifies, among the coverage indexes, a coverage index in which an elongation rate of the calculated value shows a predetermined tendency, as a preferential coverage index that is to be used preferentially, when either the number of executions of the tests or the number of bugs in the test result exceeds a predetermined standard.
-
-
-
-
-
-
搜索结果
7 条记录 (耗时 0.01 秒)
