Sony Corporation

Oki Electric Industry Co., Ltd.

Mitsubishi Heavy Industries Limited

Nitto Boseki Co., Ltd.

Kabushiki Kaisha Toshiba

Mitsubishi Electric Corporation

Toshiba Infrastructure Systems & Solutions Corporation

Kohei Yamamoto

Kurato Maeno

Masayuki Hattori

Takashi Yokokawa

Toshiyuki Miyauchi

Naoyuki Furuta

Motoko Kagaya

Yutaka Shono

Masahito Watanabe

Nobuyuki Takahashi

Hiroyuki Fujiwara

Sho Sato

Makoto Iwasaki

Kazuaki Yuuki

Toshihisa Hyakudai

Yasuhiro Iida

Masaaki Katayama

Kazuo Hirota

Norihiro Murayama

Mitsuru Ikeda

Shingo Nishida

Yoichi Iwamoto

Tomoyuki Makino

Ryoichi Kawakami

Kazuya Nakamura

Ryoichi Ikeda

Hideyuki Shimizu

Jiro Hara

Masatomo Miyashita

Toshifumi Nariai

Kaina Teshima

Sakio Nishimiya

Sonoko Miyajiri

Tetsuya Arikawa

An information processing unit includes: an attention module having an attention layer and a computation section and that is for a neural network including plural levels of layer, the attention layer being configured to compute an output feature corresponding to an input feature from a predetermined layer and based on a parameter; the computation section that multiplies the input feature by the output feature, and outputs a computed result to a layer at a next level; the first learning unit connected to the neural network and that learns the parameter in a state in which learning has been suspended at least for the predetermined layer and the next level layer; and the channel selection section that selects as a redundant channel a channel satisfying a predetermined relationship between the output feature and a predetermined threshold value.

Neural network load reduction device, information processing unit, and neural network load reduction method and computer-readable storage medium

There is provided a neural network reduction device including: an input section configured to acquire a first neural network including a plurality of processing layers that includes at least one convolutional layer; a generation section configured to generate a third neural network in which at least one second neural network is connected as an additional layer to a stage subsequent to the convolutional layer included in the first neural network; a learning section configured to train the third neural network; a correction section configured to select, as a redundant channel, a channel whose feature value calculated on a basis of a weight parameter of the second neural network establishes a predetermined relationship with a predetermined threshold, delete the redundant channel from the convolutional layer, and correct a weight parameter of the convolutional layer after deletion of the redundant channel on a basis of at least a portion of the weight parameter of the second neural network; a relearning section configured to retrain the third neural network on a basis of correction of the weight parameter of the convolutional layer after the deletion of the redundant channel; and an output section configured to output the retrained third neural network.

Neural network reduction device, neural network reduction method, and storage medium

It is possible to improve estimation accuracy with regard to data in which significance is attached to a relative phase. Provided is an information processing device including an estimation unit configured to estimate a status by using a neural network. The neural network includes a first complex-valued neural network to which complex data is input, a phase difference computation layer from which phase difference for each element between a plurality of sets with regard to the complex data is output, and a second complex-valued neural network from which complex data is output on the basis of the phase difference.

Information processing device and information processing method

A circuit system for a railroad vehicle according to an embodiment includes a power conversion unit, a first converter, a second converter, a power storage unit, and a control unit. The power conversion unit converts power supplied from an overhead wire into power for driving a motor for running mounted on a railroad vehicle. The first converter converts power supplied from the overhead wire into DC power. The second converter converts power output from the first converter into power for driving a load mounted on the railroad vehicle. The power storage unit is electrically connected to an input side of the second converter. The control unit inputs regenerative power output from the power conversion unit to the first converter and inputs power output from the first converter to the power storage unit in a case where it is determined that the railroad vehicle is being regenerated.

Circuit system for railroad vehicle

There is provided a contact force evaluation method for evaluating a contact force against a supporting member of a tube bundle positioned in a fluid and supported by the supporting member, including a contact force setting step of setting a contact force of the tube bundle, a probability density function calculation step of calculating a probability density function of a reaction force received by the supporting member from the tube bundle in response to a predetermined input, using a vibration analysis model of the tube bundle and the supporting member, a probability calculation step of calculating a probability that a reaction force equal to or higher than the set contact force occurs, based on the calculated probability density function, and an evaluation step of evaluating the set contact force, based on the calculated probability.

Contact force evaluation method

A biaxial load test specimen includes a main body and four arms. The main body has a plurality of through-holes aligned along axial directions of two load axes orthogonal to each other. The four arms extend from the main body in the respective axial directions of the load axes. Each of the arms has a plurality of slit grooves extending, on respective extensions of the through-holes aligned in the axial directions, along the respective axial directions.

Biaxial load test specimen, biaxial load test apparatus, and biaxial load test method

An estimation device includes a first converting unit configured to convert a beat signal to a one-dimensional first candidate signal on the basis of a two-dimensional distribution of the beat signal, a second converting unit configured to convert the beat signal to a one-dimensional second candidate signal on the basis of a two-dimensional position change of the beat signal, and a signal deciding unit configured to decide a one-dimensional signal on the basis of the first candidate signal and the second candidate signal.

Estimation device, vibration state estimation method, and recording medium

A tracking apparatus, including (1) a first target object tracking unit having a first processor, configured to correct a first information of at least one first candidate target object, detected by an image sensor, according to a first predetermined motion model, and to determine a distribution of the first information, (2) a second target object tracking unit including a second processor, configured to correct a second information of at least one second candidate target object, detected by an active type sensor, according to a second predetermined motion model, and to determine a distribution of the second information, (3) a matching unit configured to obtain a plurality of distribution parameters based on a correlation of the distributions of the first and second information, and (4) a false image determining unit configured to determine whether or not the second information corresponds to a false image based on the plurality of distribution parameters.

Tracking apparatus, tracking method, and computer-readable storage medium

Included are an NC command input unit that receives an NC command serving as an NC command that enables processing independent of NC machining and that is independent of a model of an NC machine tool and an NC command; a machine information storage unit; a tool information storage unit; a command analysis unit that determines whether an NC command input to the NC command input unit is the NC command; a command creation unit that, creates a designated operation program that enables the NC machine tool to perform a series of operations corresponding to the NC command on the basis of the NC command, the model information, and the tool information; and a CNC control unit that controls the NC machine tool.

Numerical control apparatus

Disclosed herein is a digital broadcast receiving apparatus configured to receive terrestrial digital television broadcasting and satellite digital broadcasting, including: a terrestrial digital tuner; a satellite digital tuner; a demodulating block configured to demodulate a reception signal of the terrestrial digital television broadcasting with an output supplied from the terrestrial digital tuner, and, at the same time, demodulate a reception signal of the satellite digital broadcasting with an output supplied from the satellite digital tuner; a terrestrial digital tuner control block; a satellite digital tuner control block; and a switching block configured to switch output terminals of the demodulating block in accordance with a positional arrangement of the terrestrial digital tuner and the satellite digital tuner relative to the demodulating block.

Digital broadcast receiving apparatus

An electronic apparatus is provided and includes a first IC having an internal configuration section, a nonvolatile memory, and an interface section. The electronic apparatus also includes a second IC having a signal processing section, and a correction-data supplying section.

Electronic apparatus, electronic-apparatus adjustment method and integrated circuit

The present invention is particularly applied to serial concatenated coding and serial concatenated trellis coded modulation. In second encoding, which is inner coding, a sequence that is not encoded or that is encoded so as to produce a finite impulse response and a sequence that is encoded so as to produce an infinite impulse response are output. In interleavingbefore the second encoding, the sequences are permuted so as not to be mixed with each other.

Encoding device for performing serial concatenated coding

An encoding device in a data transmission/reception system includes a first convolutional encoder that encodes an outer code, an interleaver that permutes input data, a second convolutional encoder that encodes an inner code, and a muti-level modulation mapping circuit that performs signal-point mapping based on eight-phase shift keying. When the encoding device uses the second convolutional encoder having two or more memories, the first convolutional encoder uses, as the outer code, a code with a minimum output distance greater than the maximum input distance at which the minimum-distance inner code is generated.

Encoding device and method and decoding device and method

A pseudo product code decoder effects error correction by using parity symbols of a first linear-structure error correction code contained in an input symbol train that constitutes a pseudo product code and by using parity symbols of a second linear-structure error correction code. Second-series information symbols are extracted from the symbol train; and a subtraction code of a pseudo product code codeword is formed of the second-series information symbols, with the first-series information symbol portion and the second linear-structure error correction code portion being changed to zero codes. The pseudo product code codeword is transformed into a product code codeword by subtracting processing with the subtraction code. Decoding processing is performed a plurality of times on the symbol train of the product code codeword, thereby effecting error correction; and first-series information symbols are extracted from the error corrected symbol train.

Pseudo product code encoding and decoding apparatus and method

First, sound absorbing plates made of a hard material are fixed to both side plates of shaped steel members extending upward from a sound insulation wall at intervals that are equal to arrangement spans of the shaped steel members. Then, sound absorbing members that have been formed into a predetermined shape and length are attached to outer surfaces of the sound insulation plates.

Growing community of inventors

Tokyo, Japan

Kohei Yamamoto