专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

41. 发明申请

US20220321641A1 Distributed Deep Learning System 有权
公开(公告)号：US20220321641A1
公开(公告)日：2022-10-06
申请号：US17627346
申请日：2019-07-16
申请人： Nippon Telegraph and Telephone Corporation
发明人： Tsuyoshi Ito , Kenji Kawai , Junichi Kato , Huycu Ngo , Yuki Arikawa , Takeshi Sakamoto , Kenji Tanaka
IPC分类号： H04L67/10 , H04L67/2866 , G06N3/08
摘要： A distributed deep learning system according to an embodiment includes M distributed processing nodes that perform deep learning of a neural network distributed from each other, and N aggregation processing nodes that are connected to each of the M distributed processing nodes via a first communication line and a second communication line, and perform aggregation of distributed processing results obtained at the M distributed processing nodes via the first communication line. Accordingly, even in a case of a plurality of users sharing the distributed deep learning system at the same time, efficient and stable distributed deep learning processing can be realized.

42. 发明申请

US20220261620A1 Distributed Processing System and Distributed Processing Method 有权
公开(公告)号：US20220261620A1
公开(公告)日：2022-08-18
申请号：US17596070
申请日：2019-06-03
申请人： Nippon Telegraph and Telephone Corporation
发明人： Kenji Kawai , Junichi Kato , Huycu Ngo , Yuki Arikawa , Tsuyoshi lto , Takeshi Sakamoto
IPC分类号： G06N3/063 , G06N3/08
摘要： A distributed processing node transmits distributed data for M groups as intermediate consolidated data from M communication units to a distributed processing node. A distributed processing node generates, for each group, updated intermediate consolidated data from the received intermediate consolidated data and distributed data, and transmits the updated intermediate consolidated data from the M communication units to a distributed processing node. The distributed processing node transmits the received intermediate consolidated data to a distributed processing node as consolidated data. The distributed processing node transmits the received consolidated data to a distributed processing node. Each of the distributed processing nodes updates weights of a neural network, based on the consolidated data.

43. 发明申请

US20210216855A1 Distributed Deep Learning System, Distributed Deep Learning Method, and Computing Interconnect Device 有权
公开(公告)号：US20210216855A1
公开(公告)日：2021-07-15
申请号：US17255209
申请日：2019-05-27
申请人： Nippon Telegraph and Telephone Corporation
发明人： Junichi Kato , Kenji Kawai , Huycu Ngo , Yuki Arikawa , Tsuyoshi Ito , Takeshi Sakamoto
IPC分类号： G06N3/04 , G06N3/063 , G06N5/04
摘要： A distributed deep learning system that can achieve speeding-up by processing learning in parallel at a large number of learning nodes connected with a communication network and perform faster cooperative processing among the learning nodes connected through the communication network is provided. The distributed deep learning system includes: a plurality of computing interconnect devices 1 connected with each other through a ring communication network 3 through which communication is possible in one direction; and a plurality of learning nodes 2 connected with the respective computing interconnect devices 1 in a one-to-one relation, and each computing interconnect device 1 executes communication packet transmission-reception processing between the learning nodes 2 and All-reduce processing simultaneously in parallel.

44. 发明申请

US20210209443A1 Distributed Processing System and Distributed Processing Method 有权
公开(公告)号：US20210209443A1
公开(公告)日：2021-07-08
申请号：US16973717
申请日：2019-05-05
申请人： Nippon Telegraph and Telephone Corporation
发明人： Kenji Kawai , Junichi Kato , Huycu Ngo , Yuki Arikawa , Tsuyoshi Ito , Takeshi Sakamoto
IPC分类号： G06N3/04 , G06N3/08
摘要： A first distributed processing node sets, as intermediate aggregated data, distributed data generated by the own node and transmits this data to the distributed processing node having the next number designated in advance. The intermediate distributed processing node excluding the first and last distributed processing nodes calculates, for each of weights corresponding thereto, a sum of the received intermediate aggregated data and distributed data generated by the own node, generates intermediate aggregated data after update, and transmits this data to the distributed processing node having the next number designated in advance. The last distributed processing node calculates, for each of the weights corresponding thereto, a sum of the received intermediate aggregated data and distributed data generated by the own node, generates aggregated data, and transmits this data to the first and intermediate distributed processing nodes. The distributed processing nodes update the weights of a neural network based on this data.

45. 发明申请

US20210034978A1 Distributed Deep Learning System 有权
公开(公告)号：US20210034978A1
公开(公告)日：2021-02-04
申请号：US16967702
申请日：2019-02-06
申请人： Nippon Telegraph and Telephone Corporation
发明人： Junichi Kato , Kenji Kawai , Huycu Ngo , Yuki Arikawa , Tsuyoshi Ito , Takeshi Sakamoto
IPC分类号： G06N3/08 , G06N3/04 , G06N3/063
摘要： Each of learning nodes calculates gradients of a loss function from an output result obtained by inputting learning data to a learning target neural network, converts a calculation result into a packet, and transmits the packet to a computing interconnect device. The computing interconnect device receives the packet transmitted from each of the learning nodes, acquires a value of the gradients stored in the packet, calculates a sum of the gradients, converts a calculation result into a packet, and transmits the packet to each of the learning nodes. Each of the learning nodes receives the packet transmitted from the computing interconnect device and updates a constituent parameter of a neural network based on a value stored in the packet.

46. 发明申请

US20140219654A1 OPTICAL NETWORK SYSTEM 有权
标题翻译：光网络系统
公开(公告)号：US20140219654A1
公开(公告)日：2014-08-07
申请号：US14234780
申请日：2012-10-12
申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION
发明人： Takashi Mitsui , Youichi Fukada , Takeshi Sakamoto , Naoto Yoshimoto
IPC分类号： H04Q11/00 , H04B10/27
CPC分类号： H04Q11/0005 , H04B10/032 , H04B10/27 , H04Q11/0067 , H04Q2011/0037 , H04Q2011/0043 , H04Q2011/0081 , H04Q2011/0088
摘要： A normal system OSU, a redundancy system OSU, an optical switch, a concentration switch, and a controller which detects a command input by operation control and performs control according to the command are provided, and in such a state that the controller detects a redundancy system switching command indicating that the normal system OSU is switched to the redundancy system OSU, the controller induces the concentration switch to change a storage destination of a down signal, instructs the normal system OSU which is the switching source OSU to stop transmission of a transmission permission message, instructs the optical switch to switch a path after receiving remaining data processing completion notifications from the concentration switch and the normal system OSU which is the switching source OSU, writes accumulated information about the normal system OSU, which is the switching source OSU, in the redundancy system OSU, and notifies the concentration switch of completion of switching, whereby a down signal is transmitted from the concentration switch.
摘要翻译：提供了通常的系统OSU，冗余系统OSU，光开关，浓度开关和控制器，其检测通过操作控制输入的命令并根据该命令进行控制，并且在控制器检测到冗余指示正常系统OSU切换到冗余系统OSU的系统切换命令，控制器引导浓度切换来改变下行信号的存储目的地，指示作为切换源OSU的正常系统OSU停止传输指示光开关在从浓度开关和作为开关源OSU的正常系统OSU接收到剩余数据处理完成通知之后切换路径，写入关于作为开关源OSU的正常系统OSU的累积信息，在冗余系统OSU中，通知集中切换完成切换，从而从浓度开关发送降低信号。

47. 发明授权

US12010554B2 Scheduling system and method 有权
公开(公告)号：US12010554B2
公开(公告)日：2024-06-11
申请号：US17298991
申请日：2019-12-13
申请人： Nippon Telegraph and Telephone Corporation
发明人： Yuki Arikawa , Takeshi Sakamoto
IPC分类号： H04W28/16 , H04W72/12
CPC分类号： H04W28/16 , H04W72/12
摘要： In a scheduling calculation unit, a setting parameter value, such as channel information, can be set in a short time period. A scheduling system includes: a transfer source process unit that compresses M-bit information (M is an integer of two or more) obtained from user equipment, to N bits (N N, L is an integer of two or more), and stores the expanded information; and a scheduling calculation unit that identifies an optimal combination pattern between a transmission point and the user equipment, using L-bit information stored in the transfer destination process unit.

48. 发明公开

US20240184965A1 CALCULATION RESOURCE CONTROL DEVICE AND CONTROL METHOD 审中-公开
公开(公告)号：US20240184965A1
公开(公告)日：2024-06-06
申请号：US18554287
申请日：2021-04-28
申请人： Nippon Telegraph and Telephone Corporation
发明人： Yuki Arikawa , Kenji Tanaka , Tsuyoshi Ito , Tsutomu Takeya , Takeshi Sakamoto
IPC分类号： G06F30/337 , G06F119/02
CPC分类号： G06F30/337 , G06F2119/02
摘要： A calculation resource control device includes an input unit to which a processing content specified by a user is input, an equivalent circuit preparation unit that collects candidates for an equivalent circuit that is a processing circuit having a function of executing a part of the processing content to output an equivalent circuit candidate group, and a function chain creation unit that determining a processing execution circuit from the equivalent circuit candidate group on the basis of a predetermined reference, determines a connection order of the processing execution circuit, and outputs a function chain for executing the processing content.

49. 发明公开

US20230385603A1 NEURAL ARCHITECTURE SEARCH SYSTEM AND SEARCH METHOD 审中-公开
公开(公告)号：US20230385603A1
公开(公告)日：2023-11-30
申请号：US18249723
申请日：2020-11-12
申请人： Nippon Telegraph and Telephone Corporation
发明人： Yuki Arikawa , Kenji Tanaka , Tsuyoshi Ito , Tsutomu Takeya , Takeshi Sakamoto
IPC分类号： G06N3/04 , G06N3/08
CPC分类号： G06N3/04 , G06N3/08
摘要： A neural architecture search system includes a deployment constraint management unit that converts a first constraint condition that defines a constraint of a system that implements a neural network into a second constraint condition that defines a constraint of a parameter that prescribes an architecture of the neural network, a learning engine unit that performs learning of the neural network under a search condition and calculates inference accuracy in a case where the learned neural network is used, and a model modification unit that causes the learning engine unit to perform the learning and the calculation of the inference accuracy while changing the architecture of the neural network on the basis of the inference accuracy and the second constraint condition so as to obtain the best inference accuracy.

50. 发明申请

US20220398431A1 Distributed Deep Learning System and Data Transfer Method 有权
公开(公告)号：US20220398431A1
公开(公告)日：2022-12-15
申请号：US17775549
申请日：2019-11-13
申请人： Nippon Telegraph and Telephone Corporation
发明人： Kenji Tanaka , Yuki Arikawa , Kenji Kawai , Junichi Kato , Tsuyoshi Ito , Huycu Ngo , Takeshi Sakamoto
IPC分类号： G06N3/04 , G06N3/08
摘要： Provided is a distributed deep learning system including a plurality of distributed processing nodes, in which each of the plurality of distributed processing nodes includes a header reading unit configured to read pieces of layer information of headers of a first data frame that has arrived at an own node and a second data frame that has arrived next, and in which the pieces of layer information are compared with each other, calculation processing is executed for a data frame including data that belongs to a layer closer to an input layer, and calculation processing for a data frame including data that belongs to a layer closer to an output layer is skipped.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式