Abstract: 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.

Abstract: A non-transitory computer-readable recording medium stores a machine learning program for causing a computer to execute a process including: allocating processors to each group of one or more layers of a neural network, and causing the processors to execute machine learning by pipeline parallel processing in units of micro-batches obtained by dividing a mini-batch which is one unit of training data used for parameter update of the neural network; and performing setting such that, as a part of backward propagation for each of the micro-batches before the parameter update by each of the processors, backward propagation of a larger number of micro-batches is omitted for a processor allocated to a group of layers closer to an input of the neural network and backward propagation of a smaller number of micro-batches is omitted for a processor allocated to a group of layers closer to an output of the neural network.

Abstract: A non-transitory computer-readable recording medium storing a machine learning program of controlling machine learning of distributed neural network models generated by dividing a neural network, the machine learning program including instructions for causing a processor to execute processing including: adding, for each of the distributed neural network models, an individual noise for that distributed neural network model to a non-parallel processing block in that distributed neural network model such that the individual noise for that distributed neural network model is different from the individual noise for other distributed neural network models from among the distributed neural network models; and assigning, to a plurality of processes, the distributed neural network models added with the individual noise to cause each of the plurality of processes to perform the machine learning on an assigned neural network model from among the distributed neural network models added with the individual noise.

Abstract: 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.

Abstract: A non-transitory computer-readable recording medium storing a check program for causing a computer to execute processing including: acquiring neural networks to be compared; dividing the acquired neural networks to be compared into respective comparable partial neural networks from beginnings; inputting same data to the respective divided partial neural networks and comparing output results for the input data; and repeating the division processing and the comparison processing until end of the neural networks in a case where the output results are determined to be equal.

Abstract: 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.

Abstract: An information processing apparatus includes: a memory; and a processor configured to: acquire an instruction sequence including plural instructions; generate plural candidates of new instruction sequences capable of obtaining an execution result as same as in the instruction sequence, by replacing at least a part of plural nop instructions included in the instruction sequence with a wait instruction that waits for completion of all preceding instructions; delete any one of the nop instructions and the wait instruction from each of the new instruction sequences, when the execution result does not change in case any one of the nop instructions and the wait instruction is deleted from the new instruction sequences in the candidates; and select a one candidate among the candidates subjected to the delete, the one candidate including the number of instructions equal to or less than a certain number, and having a smallest number of execution cycles.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: Provided is a reaction-curable adhesive that exhibits an excellent adhesive strength even under a low-temperature environment. The reaction-curable adhesive includes an epoxy compound and an amine compound, the reaction-curable adhesive being cured through a reaction between the epoxy compound and the amine compound, in which a compound having a specific molecular structure is used as at least one of the epoxy compound or the amine compound.

Abstract: An information processing apparatus includes: a memory; and a processor configured to: acquire an instruction sequence including plural instructions; generate plural candidates of new instruction sequences capable of obtaining an execution result as same as in the instruction sequence, by replacing at least a part of plural nop instructions included in the instruction sequence with a wait instruction that waits for completion of all preceding instructions; delete any one of the nop instructions and the wait instruction from each of the new instruction sequences, when the execution result does not change in case any one of the nop instructions and the wait instruction is deleted from the new instruction sequences in the candidates; and select a one candidate among the candidates subjected to the delete, the one candidate including the number of instructions equal to or less than a certain number, and having a smallest number of execution cycles.

Abstract: Provided is a reaction-curable adhesive that exhibits an excellent adhesive strength even under a low-temperature environment. The reaction-curable adhesive includes an epoxy compound and an amine compound, the reaction-curable adhesive being cured through a reaction between the epoxy compound and the amine compound, in which a compound having a specific molecular structure is used as at least one of the epoxy compound or the amine compound.