Patents Assigned to KDDI Research, Inc.
-
Patent number: 12182702Abstract: According to an aspect of the present disclosure, a method executed by an information processing apparatus in order to cause a neural network to learn a Tth task corresponding to a Tth learning set is provided. The method includes: for each of a plurality of units, determining an importance degree of the unit in the Tth task; for each of a plurality of layers, determining dissimilar tasks from among a first task to a (T?1)th task, the dissimilar tasks being not similar to the Tth task in terms of behaviors in the layer; and in learning that uses the Tth learning set, suppressing updating of weight parameters of the plurality of units included in the plurality of layers in accordance with importance degrees in the dissimilar tasks determined for each of the plurality of layers.Type: GrantFiled: September 22, 2021Date of Patent: December 31, 2024Assignees: KDDI Research, Inc., THE BOARD OF TRUSTEES OF THE UNIVERSITY OF ILLINOISInventors: Tatsuya Konishi, Mori Kurokawa, Bing Liu, Gyuhak Kim, Zixuan Ke
-
Publication number: 20240251280Abstract: A control device controlling allocation of resources in a radio access network includes: a resource usage rate acquiring unit configured to acquire a resource usage rate for each service; a total received data volume information acquiring unit configured to acquire total received data volume information indicating a total received data volume for each service received by user equipment via an interface with a base station; a total traffic volume information acquiring unit configured to acquire total traffic volume information indicating a total traffic volume for each service for the user equipment in the base station via the interface with the base station; a communication quality degradation degree calculating unit configured to calculate a degree of degradation of communication quality indicating a degree of degradation of a throughput based on a ratio of the total received data volume to the total traffic volume for each service; and a control unit configured to control a margin for a requested amount ofType: ApplicationFiled: February 1, 2022Publication date: July 25, 2024Applicant: KDDI Research, Inc.Inventors: Haruhisa HIRAYAMA, Shinobu NANBA, Hiroyuki SHINBO
-
Publication number: 20240155363Abstract: A base station function deployment control device includes a base station function deployment information acquisition unit configured to acquire base station function deployment information indicating a current base station function deployment in a radio access network of an open radio access network (O-RAN) specification via an interface with a service and management orchestration (SMO) function unit and a base station function deployment setting information transmission unit configured to transmit base station function deployment setting information indicating change content for changing the base station function deployment in the radio access network via the interface.Type: ApplicationFiled: February 1, 2022Publication date: May 9, 2024Applicant: KDDI Research, Inc.Inventors: Yuu TSUKAMOTO, Hiroyuki SHINBO, Shinobu NANBA
-
Publication number: 20240086678Abstract: The neural network includes layers, and the layers each include a plurality of units, the plurality of units each have a weight coefficient associated with each input to a unit, and an importance parameter indicating importance of the weight coefficient. The method includes: in learning of a task, adjusting a first weight coefficient based on the importance parameter of the first weight coefficient and a first gradient of the first weight coefficient determined using a training set; and after the learning has been completed, determining, based on the training set, respective second gradients of a plurality of second weight coefficients included in a first layer including the first weight coefficient, and calculating the importance parameter of the first weight coefficient to be used in learning of a next task based on the respective second gradients.Type: ApplicationFiled: September 7, 2022Publication date: March 14, 2024Applicants: KDDI Research, Inc., THE BOARD OF TRUSTEES OF THE UNIVERSITY OF ILLINOISInventors: Tatsuya Konishi, Mori Kurokawa, Bing Liu, Gyuhak Kim, Zixuan Ke
-
Publication number: 20230345016Abstract: Encoding efficiency for attribute information in point cloud information is improved. A point cloud encoding device includes a subsampling unit configured to preserve chroma signals of some points in a point cloud to be encoded and discard chroma signals of remaining points other than those points, and an attribute information encoding unit configured to encode the chroma signals of those points in the point cloud to be encoded and luma signals of all points.Type: ApplicationFiled: April 13, 2023Publication date: October 26, 2023Applicants: KDDI Research, Inc., University of Southern CaliforniaInventors: Shashank Nelamangala SRIDHARA, Eduardo Hernan Pavez CARVELLI, Antonio ORTEGA, Ryousuke WATANABE, Keisuke NONAKA, Kyouhei UNNO
-
Publication number: 20230342982Abstract: A point cloud coding device includes an interpolation unit configured to perform an interpolation process on a reconstructed point cloud of a coded frame with respect to attribute information in point cloud information and generating a reference frame of fractional precision, a motion estimation unit configured to perform motion estimation between the reference frame of fractional precision and the frame of integer precision to generate motion information, a prediction unit configured to generate a predicted value on the basis of the motion information, and an entropy coding unit configured to entropy-code the difference between a point cloud of the frame and the predicted value.Type: ApplicationFiled: January 17, 2023Publication date: October 26, 2023Applicants: KDDI Research, Inc., University of Southern CaliforniaInventors: Haoran HONG, Eduardo Hernan Pavez CARVELLI, Antonio ORTEGA, Ryousuke WATANABE, Keisuke NONAKA, Kyouhei UNNO
-
Publication number: 20230086727Abstract: According to an aspect of the present disclosure, a method executed by an information processing apparatus in order to cause a neural network to learn a Tth task corresponding to a Tth learning set is provided. The method includes: for each of a plurality of units, determining an importance degree of the unit in the Tth task; for each of a plurality of layers, determining dissimilar tasks from among a first task to a (T?1)th task, the dissimilar tasks being not similar to the Tth task in terms of behaviors in the layer; and in learning that uses the Tth learning set, suppressing updating of weight parameters of the plurality of units included in the plurality of layers in accordance with importance degrees in the dissimilar tasks determined for each of the plurality of layers.Type: ApplicationFiled: September 22, 2021Publication date: March 23, 2023Applicants: KDDI Research, Inc., THE BOARD OF TRUSTEES OF THE UNIVERSITY OF ILLINOISInventors: Tatsuya Konishi, Mori Kurokawa, Bing Liu, Gyuhak Kim, Zixuan Ke
-
Patent number: 11606129Abstract: The present embodiments relate to multi user detection in distributed antenna systems. A communication system may include a central processing circuitry and a plurality of access points connected to the central processing circuitry via a fronthaul interface. Each access point of the plurality of access points may include a plurality of antennas configured to receive signals from a plurality of UEs, and a local processing circuitry connected to the plurality of antennas. The local processing circuitry may be configured to estimate channel properties of a MIMO channel between the UEs and the antennas of the access point, and determine a subset of the UEs using the channel properties. The local processing circuitry may transmit data associated with the subset of wireless communication devices to the central processing circuitry for use to perform multiuser detection at the central processing circuitry.Type: GrantFiled: February 18, 2022Date of Patent: March 14, 2023Assignees: University of Southern California, KDDI Research, Inc.Inventors: Issei Kanno, Takeo Ohseki, Andreas Molisch