Fujitsu Corporation

Akihiko Kasagi

Akihiro Tabuchi

Masafumi Yamazaki

Yutaka Kai

Takumi Danjo

Takashi Arakawa

A non-transitory computer-readable recording medium storing an analysis program that causes a computer to execute a process, the process includes combining an artificial intelligence (AI) system with a plurality of deep learning models; and creating accuracy reference information for the plurality of deep learning models in a space in which accuracy evaluation information is projected in multiple dimensions, by using discrete threshold value evaluations, for the AI system.

Computer-readable recording medium storing analysis program, analysis method, and information processing device

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.

Computer-readable recording medium storing machine learning program, machine learning method, and information processing device of improving performance of learning skip in training machine learning model

An information processing method implemented by a computer includes: executing a generation processing that includes generating a first mini-batch by performing data extension processing on learning data and processing to generate a second mini-batch without performing the data extension processing on the learning data; and executing a learning processing by using a neural network, the learning processing being configured to perform first learning by using the first mini-batch, and then perform second learning by using the second mini-batch.

Information processing apparatus of controlling training of neural network, non-transitory computer-readable storage medium for storing information processing program of controlling training of neural network, and information processing method of controlling training of neural network

An arithmetic processing device includes: a memory; and a processor coupled to the memory and configured to: execute a plurality of data processes each of which is divided into a plurality of pipeline stages in parallel at different timings; measure a processing time of each of the plurality of pipeline stages; and set a priority of the plurality of pipeline stages in a descending order of the measured processing time.

Arithmetic processing device and arithmetic processing method

Each of a plurality of processors enters, to a model representing a neural network and including a common first weight, first data different from that used by the other processors, calculates an error gradient for the first weight, and integrates the gradients calculated by each processor. Each processor stores the first weight in a memory and updates the weight of the model to a second weight based on a hyperparameter value different from those used by the other processors, the integrated error gradient, and the first weight. Each processor enters common second data to the model, compares the evaluation results acquired by each processor, and selects a common hyperparameter value. Each processor updates the weight of the model to a third weight based on the selected hyperparameter value, the integrated error gradient, and the first weight stored in the memory.

Information processing apparatus and information processing method

An information processing apparatus for controlling a plurality of nodes mutually coupled via a plurality of cables, the apparatus includes: a memory; a processor coupled to the memory, the processor being configured to cause a first node to execute first processing to extract coupling relationship between the plurality of nodes, the first node being one of the plurality of nodes, being sequentially allocated from each of the plurality of nodes, the first processing including executing allocation processing that allocates unique coordinate information to the first node and allocates common coordinate information to nodes excluding the first node; executing transmission processing that causes the first node to transmit first information to each of the cables coupled to the first node; and executing identification processing that identifies a node having received the first information as neighboring node coupled to one of the plurality of cables coupled to the first node.

Information processing apparatus, information processing method and non-transitory computer-readable storage medium for storing information processing program of determining relations among nodes in N-dimensional torus structure

A method of controlling an information processing apparatus, the information processing apparatus being configured to perform learning processing by using a neural network, the method includes: executing a calculation processing that includes calculating a learning rate, the learning rate being configured to change in the form of a continuous curve such that the time from when the learning rate is at an intermediate value of a maximum value to when the learning rate reaches a minimum value is shorter than the time from when the learning processing starts to when the learning rate reaches the intermediate value of the maximum value; and executing a control processing that includes controlling, based on the calculated learning rate, an amount of update at the time when a weight parameter is updated in an update processing.

Information processing apparatus, control method, and non-transitory computer-readable storage medium for storing information processing program

A method for controlling an information processing system, the information processing system including multiple information processing devices coupled to each other, each of the multiple information processing devices including multiple main operation devices and multiple aggregate operation devices that are coupled to each other, the method includes: acquiring, by each of the aggregate operation devices, array data items from a main operation device coupled to the concerned aggregate operation device; determining the order of dimensions in which a process is executed and in which the information processing devices are coupled to each other; executing for each of the dimensions in accordance with the order of the dimensions, a process of halving the array data items and distributing the array data items to information processing devices arranged in the dimension; executing a process of transmitting, to information processing devices arranged in the dimension, operation results calculated based on data items.

Information processing system and method for controlling information processing system

An arithmetic processing circuit includes, a dividing circuit that divides a plurality of data blocks into groups of a number equal to the number of arithmetic processing circuits included in an information processing apparatus, a data selecting circuit that selects respective first data blocks from the plurality of data blocks included in the respective groups, a transmission destination selecting circuit that selects arithmetic processing circuits different from each other as respective transmission destinations from the plurality of arithmetic processing circuits for the respective first data blocks selected by the data selecting circuit based on destination number information obtained by exclusive disjunction operation on identification number information assigned to each arithmetic processing circuit and cyclic number information assigned to each group, and a transmitting circuit that transmits the respective first data blocks selected by the data selecting circuit to the respective arithmetic processing circuits selected by the transmission destination selecting circuit.

Information processing system, arithmetic processing circuit, and control method for information processing system

A computing method includes: generating first partitioned matrices by partitioning the first matrix by a least common multiple of the M and the N in the row direction and by the N in the column direction; generating second partitioned matrices by partitioning the second matrix by the M in the row direction and by the least common multiple in the column direction; adding a first product of the first partitioned matrices and the second partitioned matrices to a first result matrix; transmitting the first partitioned matrices to computing elements directly connected to that computing element out of other computing elements connected to each other in a torus-like manner in the row direction; transmitting the second partitioned matrices to computing elements directly connected to that computing element out of other computing elements connected to each other in a torus-like manner in the column direction.

Computing method, information processing apparatus, computing program, and information processing system

An information processing device includes a first memory and a processor. The processor includes a circuit and a second memory. The circuit calculates a first value from a plurality of third pixels that are located above an interpolation pixel from among a plurality of first pixels, calculates a second value from a plurality of fourth pixels that are located above the interpolation pixel from among an plurality of second pixels, calculates a third value from a plurality of fifth pixels that are located below the interpolation pixel, calculates a fourth value from a plurality of sixth pixels that are located below the interpolation pixel, calculates a first gradient value from the first and third values, calculates a second gradient value from the second and fourth values, determines an edge direction according to the first gradient value and the second gradient value, and calculates a pixel value of an interpolation pixel.

Information processing device, information processing method, and storage medium

An computer-implemented information processing method for a convolutional neural network processing input data, includes: identifying, by a computer, for each of elements of a kernel used in convolution operation, input values to be multiplied by the respective elements in the convolution operation from among input values included in the input data; calculating a sum total of identified input values; calculating, for each of the elements of the kernel, a product of the sum total and the element; calculating an average of calculated products; and performing the convolution operation within the convolutional neural network based on the average of the calculated products.

Growing community of inventors

Kawasaki, Japan

Akihiko Kasagi