Hitachi, Ltd.

Hitachi Astemo Ltd.

Riu Hirai

Goichi Ono

Daisuke Ishii

Hiroaki Ito

Shinya Sasaki

Nobuhiko Kikuchi

Yuji Ogata

Taisuke Ueta

Kunihiko Toumura

Tetsuya Uda

Eriko Takeda

Takumi Oishi

Keiki Nakamura

Tasuku Shimada

Taku Kumon

Processing time of a neural network is shortened, and the number of operations of the neural network is reduced such that a plurality of calculators can be effectively used. A neural network reduction device () that reduces the number of operations of a neural network by an operation device () including a plurality of calculators by reducing the neural network, the neural network reduction device including: a calculator allocation unit () that sets the number of calculators allocated to calculation processing of the neural network; a number-of-operations setting unit () that sets the number of operations of a reduced neural network based on the number of allocated calculators; and a neural network reduction unit () that reduces the neural network such that the number of operations of the neural network by the operation device () is equal to the number of operations set by the number-of-operations setting unit ().

Neural network compression device

An information processing terminal includes a processor, a memory, a communication unit, a container reception module, a container execution module and a sensor. The container reception module receives a container image via the communication unit. The container execution module boots the container when the container image is received and executes the application contained in the container image. The container boots the application based on the recognition situation about the sensor is recognized. The application executes a predetermined processing for sensing data acquired from the sensor.

Information processing terminal and sensing system

An information processing device includes a DNN operation unit that executes a DNN operation by a neural network including plural layers and a weight storage unit that stores a weight used in the DNN operation, and the DNN operation unit specifies data having a value larger than a predetermined threshold as operation target data among data input to a predetermined layer of the neural network, acquires a weight corresponding to the operation target data from the weight storage unit, and executes an operation of the predetermined layer based on the operation target data and the weight acquired from the weight storage unit.

Information processing device, in-vehicle control device, and vehicle control system

A computing system includes a server, and an on-vehicle device mounted on a vehicle. The server includes: a server storage part containing a learned model; a simplification part which generates a contraction information for determination of calculation precision by using the learned model and an object of inference; and a server communication part for transmitting the contraction information to the on-vehicle device. The on-vehicle device includes: a signal input part to which an output signal from a sensor mounted on the vehicle is inputted; an on-vehicle communication part for receiving the contraction information; an inference part for making an inference on the output signal and a reconfigurable logic circuit; and a reconfiguration part for configuring the inference part in the logic circuit based on the contraction information.

Computing system, server and on-vehicle device

To improve learning accuracy, while avoiding transferring of a dataset from an edge terminal to a cloud server. A management device accessible to a target object to be managed has a processor executing a program, a storage device storing the program, and a communication interface communicable with the target object. The processor executes a reception process for receiving first environmental information representing a first environment of the target object, a first generation process for generating relevant information representing relevancy between the first environmental information and second environmental information representing a second environment of the target object, a second generation process for generating a first learned model for inference by the target object in the first environment based on the relevant information and a second learned model for inference by the target object in the second environment, and a transmission process for transmitting the first learned model to the target object.

Management device, management method, and management program

Provided is a server load prediction system that predicts a server load on a server connected to an apparatus installed in a production process including an apparatus requirement specification storage unit that stores a requirement specification of each apparatus for a server, a server specification storage unit that stores a server specification indicating a capability held by each server, an input information creation unit that receives an input of a calculation condition and creates an input parameter required to execute a simulation for calculating the server load, a server load calculation unit that calculates the server load caused by the apparatus used in a process designated under the calculation condition by executing the simulation, and an output unit that outputs the calculation result.

Server load prediction system and server load prediction method

Bending of an optical fiber where a heat may be generated by a high output power can be detected without using a dedicated light source. An optical communication module that outputs a continuous wave light generated by at least one light source to an optical fiber transmission line, includes: (1) a loss measurement unit that measures a loss of an amplified spontaneous emission generated by allowing the continuous wave light output from the light source to create stimulated Raman scattering in the optical fiber transmission line; (2) a fiber abnormality analyzer that detects the abnormal state of the optical fiber transmission line on the basis of loss information on the ASE measured by the loss measurement unit; and (3) a light source controller that controls a supply state of the continuous wave light from the light source on the basis of the detection of the fiber abnormality analyzer.

Growing community of inventors

Tokyo, Japan

Riu Hirai