Patents by Inventor Yutaka Kai
Yutaka Kai has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11939177Abstract: An image forming apparatus includes a sheet accommodating portion, an image forming portion, an accommodating portion opening portion, a lifter plate, a lifter plate lifting and lowering mechanism, a lower-limit detecting portion, a control unit lowering the lifter plate and opening the accommodating portion in accordance with an operation in a set mode of a plurality of modes when the control unit receives an instruction to open the accommodating portion, wherein the modes includes a first mode in which the accommodating portion is opened irrespective of whether or not the lifter plate lowers to the lower-limit position and a second mode in which the accommodating portion is opened after the lifter plate lowers to the lower-limit position; and an operating portion operable by an operator for changing setting of the mode, between the modes, executed when the control unit receives the instruction to open the accommodating portion.Type: GrantFiled: November 20, 2020Date of Patent: March 26, 2024Assignee: Canon Kabushiki KaishaInventors: Hiroto Nishihara, Yohei Katto, Yutaka Ando, Teruhito Kai, Akihiro Kawakita
-
Publication number: 20230095268Abstract: A non-transitory computer-readable storage medium storing a machine learning program that causes at least one computer to execute a process, the process includes acquiring a first training rate of a first layer that is selected to stop training among layers included in a machine learning model during training of the machine learning model; setting a first time period to stop training the first layer based on the training rate; and training the first layer with controlling the training rate up to the first time period.Type: ApplicationFiled: June 1, 2022Publication date: March 30, 2023Applicant: FUJITSU LIMITEDInventors: Yasushi Hara, Akihiko Kasagi, Yutaka Kai, Takumi Danjo
-
Publication number: 20230083790Abstract: A computer-implemented method of a speed-up processing, the method including: calculating variance of weight information regarding a weight updated by machine learning, for each layer included in a machine learning model at a predetermined interval at time of the machine learning of the machine learning model; and determining a suppression target layer that suppresses the machine learning on the basis of a peak value of the variance calculated at the predetermined interval and the variance of the weight information calculated at the predetermined interval.Type: ApplicationFiled: June 21, 2022Publication date: March 16, 2023Applicant: FUJITSU LIMITEDInventors: Yasushi Hara, Akihiko Kasagi, YUTAKA KAI, Takumi Danjo
-
Publication number: 20220147872Abstract: A non-transitory computer-readable recording medium storing a calculation processing program for causing a computer to execute processing, the processing including: calculating error gradients of a plurality of layers of a machine learning model that includes an input layer of the machine learning model at the time of machine learning of the machine learning model; selecting a layer of which the error gradient is less than a threshold as a suppression target of the machine learning; and controlling a learning rate and performing the machine learning on the layer selected as the suppression target in a certain period of time before the machine learning is suppressed.Type: ApplicationFiled: August 30, 2021Publication date: May 12, 2022Applicant: FUJITSU LIMITEDInventors: YUTAKA KAI, Akihiko Kasagi, Yasushi Hara, Takumi Danjo
-
Publication number: 20220147772Abstract: A computer-implemented method includes: calculating error gradients with respect to a plurality of layers included in a machine learning model at a time of machine learning of the machine learning model, the plurality of layers including an input layer of the machine learning model; specifying, as a layer to be suppressed, a layer located in a range from a position of the input layer to a predetermined position among the layers in which the error gradient is less than a threshold; and suppressing the machine learning for the layer to be suppressed.Type: ApplicationFiled: July 15, 2021Publication date: May 12, 2022Applicant: FUJITSU LIMITEDInventors: YUTAKA KAI, Akihiko Kasagi, Yasushi Hara, Takumi Danjo
-
Publication number: 20210406683Abstract: A process includes starting a learning process for building a model including multiple layers each including a parameter. The learning process executes iterations, each including calculating output error of the model using training data and updating the parameter value based on the output error. The process also includes selecting two or more candidate layers representing candidates for layers, where the updating is to be suppressed, based on results of a first iteration of the learning process. The process also includes calculating, based on the number of iterations executed up to the first iteration, a ratio value which becomes larger when the number of iterations executed is greater, and determining, amongst the candidate layers, one or more layers, where the updating is to be suppressed at a second iteration following the first iteration. The number of one or more layers is determined according to the ratio value.Type: ApplicationFiled: April 9, 2021Publication date: December 30, 2021Applicant: FUJITSU LIMITEDInventors: YUTAKA KAI, Akihiko Kasagi
-
Publication number: 20210397948Abstract: A memory holds a model including a plurality of layers including their respective parameters and training data. A processor starts learning processing, which repeatedly calculates an error of an output of the model by using the training data, calculates an error gradient, which indicates a gradient of the error with respect to the parameters, for each of the layers, and updates the parameters based on the error gradients. The processor calculates a difference between a first error gradient calculated in a first iteration in the learning processing and a second error gradient calculated in a second iteration after the first iteration for a first layer among the plurality of layers. In a case where the difference is less than a threshold, the processor skips the calculating of the error gradient and the updating of the parameter for the first layer in a third iteration after the second iteration.Type: ApplicationFiled: March 10, 2021Publication date: December 23, 2021Applicant: FUJITSU LIMITEDInventors: Yasushi Hara, Akihiko Kasagi, Takumi Danjo, YUTAKA KAI
-
Publication number: 20210158212Abstract: A first learning rate is set to a first block including a first parameter, and a second learning rate, which is smaller than the first learning rate, is set to a second block including a second parameter. The first block and the second block are included in a model. Learning processing in which updating the first parameter based on a prediction error of the model, the prediction error having been calculated by using training data, and the first learning rate and updating the second parameter based on the prediction error and the second learning rate are performed iteratively is started. An update frequency of the second parameter is controlled such that this update frequency becomes lower than an update frequency of the first parameter by intermittently omitting the updating of the second parameter in the learning processing based on a relationship between the first and second learning rates.Type: ApplicationFiled: October 8, 2020Publication date: May 27, 2021Applicant: FUJITSU LIMITEDInventors: YUTAKA KAI, Akihiko Kasagi
-
Patent number: 10027408Abstract: An optical transmitter transmits to an optical receiver a multi-carrier modulated signal light by driving a light source with a modulated signal modulated with a multi-carrier modulation scheme. The optical receiver monitors reception characteristic of any of subcarrier signals included in the modulated signal and transmits a monitor result to the optical transmitter. The optical transmitter controls drive conditions of the light source based on the monitor result received from the optical receiver.Type: GrantFiled: June 10, 2016Date of Patent: July 17, 2018Assignee: FUJITSU LIMITEDInventors: Masato Nishihara, Toshiki Tanaka, Yutaka Kai, Tomoo Takahara
-
Patent number: 9998233Abstract: An optical reception apparatus may include a receiver, a monitor, and a controller. The optical reception apparatus receives multi-carrier modulated signal light modulated by a multi-carrier modulation scheme. The multi-carrier modulation scheme is available to allocate different transmission conditions for each of a plurality of subcarriers in accordance with transmission characteristics of the subcarriers. The receiver may receive from an optical transmission line a training signal light allocated with the same transmission conditions for each of the subcarriers. The monitor may monitor the transmission characteristics of the training signal light to detect a frequency at which a dip of the transmission characteristics occurs. The controller may control, based on the frequency detected by the monitor, a dispersion compensation for the multi-carrier modulated signal light having received a dispersion from the optical transmission line.Type: GrantFiled: January 11, 2016Date of Patent: June 12, 2018Assignee: FUJITSU LIMITEDInventors: Ryou Okabe, Masato Nishihara, Toshiki Tanaka, Yutaka Kai, Tomoo Takahara
-
Optical transmitter, optical communication system, and optical transmission/reception control method
Patent number: 9998230Abstract: An optical transmitter includes an optical modulator to modulate light having a predetermined wavelength into an optical signal based on a data signal, a memory, and a processor coupled to the memory and the processor configured to modulate an input signal into a multi-carrier signal so as to generate the data signal, the multi-carrier signal including a plurality of subcarriers each to which a transmission capacity is allocated, acquire a first frequency distribution of an intensity of the multi-carrier signal, acquire a second frequency distribution of an intensity of the optical signal, control the modulating of the input signal into the multi-carrier signal to change a number of subcarriers of the multi-carrier signal, and control the optical modulator to adjust a modulation characteristic of the optical modulator so that a divergence between the first frequency distribution and the second frequency distribution is equal to or less than a predetermined value.Type: GrantFiled: July 20, 2017Date of Patent: June 12, 2018Assignee: FUJITSU LIMITEDInventors: Masato Nishihara, Toshiki Tanaka, Tomoo Takahara, Ryou Okabe, Yutaka Kai -
Patent number: 9973276Abstract: An apparatus includes a receiver configured to receive a signal that has traveled an optical transmission line without returning output from an optical transmitting device and synchronize with the optical transmitting device in order to demodulate the signal; a dispersion compensator configured to compensate for wavelength dispersion caused by transmission of the signal; an acquisition circuit configured to acquire a transmitting timing at which the signal has been transmitted from the optical transmitting device; a calculation circuit configured to calculate a transmission time period from the optical transmitting device to the receiver from the transmitting timing and a receiving timing at which the signal has been received with the receiver; and an amount setting circuit configured to adjust a dispersion compensation amount of the dispersion compensator in accordance with the transmission time period.Type: GrantFiled: January 24, 2017Date of Patent: May 15, 2018Assignee: FUJITSU LIMITEDInventors: Yutaka Kai, Tomoo Takahara, Toshiki Tanaka, Masato Nishihara, Ryou Okabe
-
OPTICAL TRANSMITTER, OPTICAL COMMUNICATION SYSTEM, AND OPTICAL TRANSMISSION/RECEPTION CONTROL METHOD
Publication number: 20180034551Abstract: An optical transmitter includes an optical modulator to modulate light having a predetermined wavelength into an optical signal based on a data signal, a memory, and a processor coupled to the memory and the processor configured to modulate an input signal into a multi-carrier signal so as to generate the data signal, the multi-carrier signal including a plurality of subcarriers each to which a transmission capacity is allocated, acquire a first frequency distribution of an intensity of the multi-carrier signal, acquire a second frequency distribution of an intensity of the optical signal, control the modulating of the input signal into the multi-carrier signal to change a number of subcarriers of the multi-carrier signal, and control the optical modulator to adjust a modulation characteristic of the optical modulator so that a divergence between the first frequency distribution and the second frequency distribution is equal to or less than a predetermined value.Type: ApplicationFiled: July 20, 2017Publication date: February 1, 2018Applicant: FUJITSU LIMITEDInventors: MASATO NISHIHARA, Toshiki Tanaka, Tomoo Takahara, Ryou Okabe, YUTAKA KAI -
Patent number: 9876601Abstract: There is proved an optical transmission system including: a transmitter configured to transmit an optical signal modulated with a discrete multi-tone (DMT) drive signal; a filter capable of changing a wavelength of the optical signal input from the transmitter; a monitor configured to monitor a power of the optical signal passed through the filter; and at least one processor configured to: set a center wavelength of the filter, shift the center wavelength, detect a change in the power monitored by the monitor, identify a carrier component of the optical signal based on the change in the power, and control a relative relationship between a transmission characteristic of the filter and a wavelength of the carrier component so that the carrier component is included in the optical signal and one of an upper sideband and a lower sideband of the optical signal is at least partially removed by the filter.Type: GrantFiled: September 14, 2016Date of Patent: January 23, 2018Assignee: FUJITSU LIMITEDInventors: Toshiki Tanaka, Ryou Okabe, Tomoo Takahara, Masato Nishihara, Yutaka Kai
-
Patent number: 9853728Abstract: A bit allocation method is used in an optical transmission system that transmits multicarrier signals of different wavelengths in wavelength division multiplexing. Frequency characteristics of subcarriers included in the multicarrier signals are different between the respective multicarrier signals. The method includes: measuring transmission characteristics of the subcarriers included in corresponding multicarrier signals at different subcarrier frequencies; and determining a number of bits to be allocated to each of the subcarriers included in each of the multicarrier signals based on the transmission characteristics measured at the different subcarrier frequencies.Type: GrantFiled: August 31, 2016Date of Patent: December 26, 2017Assignee: FUJITSU LIMITEDInventors: Masato Nishihara, Toshiki Tanaka, Yutaka Kai, Ryou Okabe, Tomoo Takahara
-
Publication number: 20170272161Abstract: An apparatus includes a receiver configured to receive a signal that has traveled an optical transmission line without returning output from an optical transmitting device and synchronize with the optical transmitting device in order to demodulate the signal; a dispersion compensator configured to compensate for wavelength dispersion caused by transmission of the signal; an acquisition circuit configured to acquire a transmitting timing at which the signal has been transmitted from the optical transmitting device; a calculation circuit configured to calculate a transmission time period from the optical transmitting device to the receiver from the transmitting timing and a receiving timing at which the signal has been received with the receiver; and an amount setting circuit configured to adjust a dispersion compensation amount of the dispersion compensator in accordance with the transmission time period.Type: ApplicationFiled: January 24, 2017Publication date: September 21, 2017Applicant: FUJITSU LIMITEDInventors: Yutaka Kai, Tomoo Takahara, Toshiki Tanaka, Masato Nishihara, Ryou Okabe
-
Publication number: 20170093515Abstract: There is proved an optical transmission system including: a transmitter configured to transmit an optical signal modulated with a discrete multi-tone (DMT) drive signal; a filter capable of changing a wavelength of the optical signal input from the transmitter; a monitor configured to monitor a power of the optical signal passed through the filter; and at least one processor configured to: set a center wavelength of the filter, shift the center wavelength, detect a change in the power monitored by the monitor, identify a carrier component of the optical signal based on the change in the power, and control a relative relationship between a transmission characteristic of the filter and a wavelength of the carrier component so that the carrier component is included in the optical signal and one of an upper sideband and a lower sideband of the optical signal is at least partially removed by the filter.Type: ApplicationFiled: September 14, 2016Publication date: March 30, 2017Applicant: FUJITSU LIMITEDInventors: Toshiki Tanaka, Ryou Okabe, Tomoo Takahara, MASATO NISHIHARA, YUTAKA KAI
-
Publication number: 20170070286Abstract: A bit allocation method is used in an optical transmission system that transmits multicarrier signals of different wavelengths in wavelength division multiplexing. Frequency characteristics of subcarriers included in the multicarrier signals are different between the respective multicarrier signals. The method includes: measuring transmission characteristics of the subcarriers included in corresponding multicarrier signals at different subcarrier frequencies; and determining a number of bits to be allocated to each of the subcarriers included in each of the multicarrier signals based on the transmission characteristics measured at the different subcarrier frequencies.Type: ApplicationFiled: August 31, 2016Publication date: March 9, 2017Applicant: FUJITSU LIMITEDInventors: MASATO NISHIHARA, Toshiki Tanaka, YUTAKA KAI, Ryou Okabe, Tomoo Takahara
-
Patent number: 9467229Abstract: A multilevel-intensity modulation and demodulation system includes: a digital-to-analog conversion unit to convert an output level value of a digital signal into an analog signal; a multilevel-intensity-modulated light transmission unit to transmit an optical signal multilevel-intensity modulated based on the analog signal; a multilevel-intensity-modulated light reception unit to receive the optical signal multilevel-intensity modulated, and convert the received optical signal into an analog reception electrical signal; an analog-to-digital conversion unit to convert the analog reception electrical signal into a reception level value; and a controller to convert a transmission multiple gradation level being one of a plurality of multiple gradation levels of multilevel-intensity modulation to which the digital signal is mapped, into the output level value so as to cause the reception level value to be in a desired reception state, and to receive a digital signal corresponding to a reception multiple-gradation-Type: GrantFiled: January 22, 2015Date of Patent: October 11, 2016Assignee: FUJITSU LIMITEDInventors: Yutaka Kai, Masato Nishihara, Toshiki Tanaka, Tomoo Takahara
-
Publication number: 20160285548Abstract: An optical transmitter transmits to an optical receiver a multi-carrier modulated signal light by driving a light source with a modulated signal modulated with a multi-carrier modulation scheme. The optical receiver monitors reception characteristic of any of subcarrier signals included in the modulated signal and transmits a monitor result to the optical transmitter. The optical transmitter controls drive conditions of the light source based on the monitor result received from the optical receiver.Type: ApplicationFiled: June 10, 2016Publication date: September 29, 2016Applicant: FUJITSU LIMITEDInventors: MASATO NISHIHARA, Toshiki Tanaka, YUTAKA KAI, Tomoo Takahara