-
公开(公告)号：US20190286946A1
公开(公告)日：2019-09-19
申请号：US16274321
申请日：2019-02-13
Applicant: FUJITSU LIMITED
Inventor： Kento UEMURA , TAKASHI KATOH , Suguru YASUTOMI , Toshio Endoh
Abstract: A learning method for an auto-encoder is performed by a computer. The method includes: by using a discriminator configured to generate an estimated label based on a feature value generated by an encoder of an auto-encoder and input data, causing the discriminator to learn such that a label corresponding the input data and the estimated label are matched; and by using the discriminator, causing the encoder to learn such that the label corresponding to the input data and the estimated label are separated.
-
公开(公告)号：US20190138250A1
公开(公告)日：2019-05-09
申请号：US16176010
申请日：2018-10-31
Applicant: FUJITSU LIMITED
Inventor： TAKASHI KATOH , Keisuke GOTO
IPC: G06F3/06
Abstract: An optional array in a memory includes an array having blocks each including an address word and a data word, and a boundary that is a position where a ratio between the numbers of unwritten blocks in M area and written blocks in W area is an integer ratio. The controlling process includes when a second write for writing a special value in a written block in the second area is invoked, executing a shrink process of shifting the boundary to shrink the first area; in a case where the first adjacent block at the boundary is a written block, storing an address of the first adjacent block and of a first link destination block forming a link with the write destination block in address words of the first link destination block and of the first adjacent block respectively to form a link.
-
23.发明申请公开(公告)号：US20140114900A1
公开(公告)日：2014-04-24
申请号：US14037446
申请日：2013-09-26
Applicant: FUJITSU LIMITED
Inventor： TAKASHI KATOH , Shinichiro TAGO , Tatsuya ASAI , Hiroaki MORIKAWA , Hiroya INAKOSHI , NOBUHIRO YUGAMI
IPC: G06N5/04
CPC classification number: G06N5/047 , G06F17/30 , G06N5/04 , H04N21/8541
Abstract: According to one aspect, a computer-readable recording medium stores therein an extracting program 330a causing a computer to execute a process. The process includes based on event data obtained by associating a plurality of events stored in a storage unit and an occurrence time of each event, sequentially adding an event to a first pattern obtained by associating the plurality of events and the occurrence order of each event, and sequentially generating a second pattern which includes the first pattern and occurs in the event data; and extracting a pattern which satisfies a predetermined condition from the generated second pattern.
Abstract translation: 根据一个方面，计算机可读记录介质中存储有使计算机执行处理的提取程序330a。 该处理包括基于通过将存储在存储单元中的多个事件与每个事件的发生时间相关联而获得的事件数据顺序地将事件发送到通过关联多个事件而获得的第一模式和每个事件的发生顺序， 并顺序产生包括第一模式并发生在事件数据中的第二模式; 以及从产生的第二图案提取满足预定条件的图案。
-
公开(公告)号：US20130325761A1
公开(公告)日：2013-12-05
申请号：US13859974
申请日：2013-04-10
Applicant: FUJITSU LIMITED
Inventor： Hiroaki Morikawa , Tatsuya Asai , Shinichiro Tago , TAKASHI KATOH , Hiroya INAKOSHI , NOBUHIRO YUGAMI
IPC: G06N99/00
CPC classification number: G06N99/005 , G06K9/00785 , G06N5/025 , G06Q10/0637 , G08G1/0112 , G08G1/0129 , G08G1/20
Abstract: A method for detecting an abnormal transition pattern from a transition pattern includes: first extracting an episode pattern with an appearance frequency greater than or equal to a first frequency from an episode pattern represented with a description form so as to include a first transition pattern and a second transition pattern differing in an order of a part of items from the first transition pattern to have a complementary relation thereto; second extracting a third transition pattern with an appearance frequency greater than or equal to a second frequency from the transition pattern; and specifying a transition pattern other than the third transition pattern from transition patterns included in the extracted episode pattern, and determining an abnormal transition pattern based on the transition pattern specified in the specifying when the third transition pattern includes a fourth transition pattern corresponding to the extracted episode pattern in the first extracting.
Abstract translation: 用于从转换模式检测异常转换模式的方法包括：首先从具有描述形式的情节模式中提取具有大于或等于第一频率的出现频率的发作模式，以便包括第一过渡模式和 第二过渡模式以与第一过渡模式的一部分项目的顺序不同以具有互补关系; 从转换图案中提取具有大于或等于第二频率的出现频率的第三转换模式; 并且从包括在所提取的插曲图案中的转换图案中指定除了第三转换图案之外的转换图案，并且基于在第三转换图案包括与提取的对应的第四转换模式相关的第四转换模式时在指定中指定的转换模式来确定异常转换模式 情节模式在第一次提取。
-
公开(公告)号：US20240232231A1
公开(公告)日：2024-07-11
申请号：US18610415
申请日：2024-03-20
Applicant: Fujitsu Limited
Inventor： Kanata SUZUKI , Taro SUNAGAWA , Tomotake SASAKI , TAKASHI KATOH
IPC: G06F16/28
CPC classification number: G06F16/285
Abstract: A non-transitory computer-readable recording medium has stored therein a data gathering program executable by one or more computers, the data gathering program including: performing data augmentation on unlabeled data; providing a specification label to a group of augmented data pieces generated by the data augmentation, the specification label indicating that labels of the augmented data pieces all match; and providing, when a label for one data piece of the augmented data pieces is determined, the label to one or more data pieces each provided with a specification label that is same as a specification label of the one data piece.
-
Patent Agency Ranking
公开(公告)号：US20220237407A1
公开(公告)日：2022-07-28
申请号：US17723599
申请日：2022-04-19
Applicant: FUJITSU LIMITED
Inventor： YUHEI UMEDA , TAKASHI KATOH , Yuichi Ike , Mari Kajitani , Masatoshi Takenouchi
Abstract: A non-transitory computer-readable storage medium storing an estimation program that causes a computer to execute a process includes specifying representative points of each of training clusters that corresponds to each of labels targeted for estimation; setting boundaries between each of input clusters under a condition that a number of the input clusters and a number of the representative points coincide with each other, the input clusters being generated by clustering in a feature space for input data; acquiring estimation results for the labels with respect to the input data based on a correspondence relationship between the input clusters and the training clusters based on the boundaries; and estimating determination accuracy for the labels by using the machine learning model with respect to the input data based on the estimation results.
-
公开(公告)号：US20210012193A1
公开(公告)日：2021-01-14
申请号：US16921944
申请日：2020-07-07
Applicant: FUJITSU LIMITED
Inventor： Suguru YASUTOMI , TAKASHI KATOH , Kento UEMURA
Abstract: A machine learning method includes: calculating, by a computer, a first loss function based on a first distribution and a previously set second distribution, the first distribution being a distribution of a feature amount output from an intermediate layer when first data is input to an input layer of a model that has the input layer, the intermediate layer, and an output layer; calculating a second loss function based on second data and correct data corresponding to the first data, the second data being output from the output layer when the first data is input to the input layer of the model; and training the model based on both the first loss function and the second loss function.
-
28.发明申请公开(公告)号：US20200242412A1
公开(公告)日：2020-07-30
申请号：US16774100
申请日：2020-01-28
Applicant: FUJITSU LIMITED
Inventor： TAKASHI KATOH , Kazuki IWAMOTO , Kento UEMURA , Suguru YASUTOMI
Abstract: An anomaly detection apparatus performs training for the generator and the discriminator such that the generator maximizes a discrimination error of the discriminator and the discriminator minimizes the discrimination error The anomaly detection apparatus stores, while the training is being performed, a state of the generator that is half-trained and satisfies a pre-set condition, and retrains the discriminator by using an image generated by the half-trained generator that has the stored state.
-
公开(公告)号：US20200234140A1
公开(公告)日：2020-07-23
申请号：US16741860
申请日：2020-01-14
Applicant: FUJITSU LIMITED
Inventor： TAKASHI KATOH , Kento UEMURA , Suguru YASUTOMI , Takeshi OSOEKAWA
Abstract: A learning method executed by a computer, the learning method includes: learning parameters of a machine learning model having intermediate feature values by inputting a plurality of augmented training data, which is generated by augmenting original training data, to the machine learning model so that specific intermediate feature values, which are calculated from specific augmented training data augmented from a same original training data, become similar to each other.
-
公开(公告)号：US20200234139A1
公开(公告)日：2020-07-23
申请号：US16741839
申请日：2020-01-14
Applicant: FUJITSU LIMITED
Inventor： TAKASHI KATOH , Kento UEMURA , Suguru YASUTOMI
Abstract: A learning method executed by a computer, the learning method including augmenting original training data based on non-stored target information included in the original training data to generate a plurality of augmented training data, generating a plurality of intermediate feature values by inputting the plurality of augmented training data to a learning model, and learning a parameter of the learning model such that, with regard to the plurality of intermediate feature values, each of the plurality of intermediate feature values generated from a plurality of augmented training data, augmented from reference training data, becomes similar to a reference feature value.
-
-
-
-
-
-
-
-
-
Search Results
33
records
(took 0.015 seconds)
