Abstract: A hyperparameter configuration device includes at least one memory, and at least one processor configured to acquire a program execution instruction including parameter description data, the program execution instruction being written through a command-line interface, set a value of a hyperparameter of a program to be trialed, based on the parameter description data, acquire a result of a trial of the program, the trial of the program being executed with the value of the hyperparameter, and set a next value of the hyperparameter of the program, based on the result of the trial.

Abstract: A hyperparameter tuning method for execution by one or more processors includes receiving a request to obtain a hyperparameter, the request being generated according to a hyperparameter obtaining code, and the hyperparameter obtaining code being written in a user program, and providing the hyperparameter to the user program based on an application history of hyperparameters applied to the user program.

Abstract: To enable disease affection determination by using a neural network to perform learning using data of the expression levels of biomarkers, and to enable extraction of a feature biomarker for a disease by the neural network.

Abstract: According to one embodiment, a gradient compressing apparatus includes a memory and processing circuitry. The memory stores data. The processing circuitry is configured to calculate statistics of gradients calculated regarding a plurality of parameters being learning targets, with respect to an error function in learning; determine, based on the statistics, whether or not to be a transmission parameter being a parameter which transmits gradients regarding each of the parameters, via a communication network; and quantize a gradient representative value being a representative value of gradients regarding the parameter determined to be a transmission parameter.

Abstract: An image processing system for generating an attack image includes an attack network, and a plurality of image classification networks for an attack target, each including different characteristics. The attack network generates the attack image by performing forward processing on a given image. Each of the image classification networks classifies the attack image by performing forward processing on the attack image, and calculates gradients making a classification result inaccurate by performing backward processing. The attack network performs learning by using the gradients calculated by the plurality of image classification networks.

Abstract: A distributed deep learning device that exchanges a quantized gradient with a plurality of learning devices and performs distributed deep learning, that includes: a communicator that exchanges the quantized gradient by communication with another learning device; a gradient calculator that calculates a gradient of a current parameter; a quantization remainder adder that adds, to the gradient, a value obtained by multiplying a remainder at the time of quantizing a previous gradient by a predetermined multiplying factor; a gradient quantizer that quantizes the gradient obtained by the quantization remainder adder; a gradient restorer that restores a quantized gradient received by the communicator to a gradient of the original accuracy; a quantization remainder storage that stores a remainder at the time of quantizing; a gradient aggregator that aggregates gradients collected by the communicator and calculates an aggregated gradient; and a parameter updater that updates the parameter with the aggregated gradient.