Fujitsu Corporation

Kento Uemura

Takashi Katoh

Suguru Yasutomi

Toshio Endoh

Hiroya Inakoshi

Kazuki Iwamoto

Keisuke Goto

Takeshi Osoekawa

Yuiko Ohta

A learning device executes learning of a discriminator that discriminates object data to a known class included in training data or an unknown class not included in the training data, using the training data. The learning device then generates a feature value of the unknown class, from a feature value of a plurality of layers of the discriminator, by at least a part of the training data in the layers. The learning device then executes the learning of the discriminator so that a feature value of the known class and the generated feature value of the unknown class are separated.

Computer-readable recording medium, method for learning, and learning device

A learning method executed by a computer, the learning method including augmenting original training data based on non-stored target information included in the original training data to generate a plurality of augmented training data, generating a plurality of intermediate feature values by inputting the plurality of augmented training data to a learning model, and learning a parameter of the learning model such that, with regard to the plurality of intermediate feature values, each of the plurality of intermediate feature values generated from a plurality of augmented training data, augmented from reference training data, becomes similar to a reference feature value.

Learning method, learning apparatus, and computer-readable recording medium

A learning method executed by a computer, the learning method includes: learning parameters of a machine learning model having intermediate feature values by inputting a plurality of augmented training data, which is generated by augmenting original training data, to the machine learning model so that specific intermediate feature values, which are calculated from specific augmented training data augmented from a same original training data, become similar to each other.

Learning method, and learning apparatus, and recording medium

A learning device generates a first feature value and a second feature value by inputting original training data to a first neural network included in a learning model. The learning device learns at least one parameter of the learning model and a parameter of a decoder, reconstructing data inputted to the first neural network, such that reconstruction data outputted from the decoder by inputting the first feature value and the second feature value to the decoder becomes close to the original training data, and that outputted data that is outputted from a second neural network, included in the learning model by inputting the second feature value to the second neural network becomes close to correct data of the original training data.

Learning method, non-transitory computer readable recording medium, and learning device

A non-transitory computer-readable recording medium stores therein a learning program that causes a computer to execute a process including: generating a shadow image including a shadow according to a state of ultrasound reflection in an ultrasound image; generating a combined image by combining the ultrasound image and the shadow image; inputting, into a first decoder and a second decoder, an output acquired from an encoder in response to inputting the combined image into the encoder; and executing training of the encoder, the first decoder, and the second decoder, based on: reconfigured error between an output image of a coupling function and the combined image, the coupling function being configured to combine a first image output from the first decoder with a second image output from the second decoder, and an error function between an area in the first image and the shadow in the shadow image.

Learning apparatus, learning method, and recording medium

A non-transitory computer-readable recording medium has stored therein a program that causes a computer to execute a process, the process including: obtaining an estimation value of a third variable by subtracting a second output value of a second parametric model to which a second variable is input from a first output value of a first parametric model to which a first variable is input; performing first parameter update of updating first parameters of the first parametric model and second parameters of the second parametric model such that independence between the second variable and the estimation value of the third variable is maximized; and updating the first parameters and third parameters of a third parametric model in the first parameter update, such that a third output value of the third parametric model is approximated to the first variable, the third parametric model being input with the first output value.

Method of updating parameters and information processing apparatus

An apparatus receives, at a discriminator within a generative adversarial network, first generation data from a first generator within the generative adversarial network, where the first generator has performed learning using a first data group. The apparatus receives, at the discriminator, a second data group, and performs learning of a second generator based on the first generation data and the second data group where the first generation data is handled as false data by the discriminator.

Sequential learning maintaining a learned concept

A learning device learns at last one parameter of a learning model such that each intermediate feature quantity becomes similar to a reference feature quantity, the each intermediate feature quantity being calculated as a result of inputting a plurality of sets of augmentation training data to a first neural network in the learning model, the plurality of augmentation training data being generated by performing data augmentation based on same first original training data. The learning device learns at last one parameter of a second network, in the learning model, using second original training data, which is different than the first original training data, and using the reference feature quantity.

Method, recording medium, and device for utilizing feature quantities of augmented training data

A non-transitory computer-readable storage medium storing a program that causes a computer to execute a process, the process including obtaining a feature quantity of input data by using a feature generator, generating a first output based on the feature quantity by using a supervised learner for labeled data, generating a second output based on the feature quantity by using an unsupervised learning processing for unlabeled data, and changing a contribution ratio between a first error and a second error in a learning by the feature generator, the first error being generated from the labeled data and the first output, the second error being generated from the unlabeled data and the second output.

Non-transitory computer-readable storage medium, learning method, and learning device

An anomaly detection apparatus generates pieces of image data using a generator and train the generator and a discriminator that discriminates whether an image data, generated by the generator, is real or fake. The anomaly detection apparatus trains the generator such that the generator, in generating the pieces of image data to maximize the discrimination error of the discriminator, generate at least a piece of specified image data to reduce the discrimination error at a fixed rate with respect to the pieces of image data and trains, based on the pieces of image data and the at least a piece of specified image data, the discriminator to minimize the discrimination error.

Training apparatus, training method, and non-transitory computer-readable recording medium

An anomaly detection apparatus performs training for the generator and the discriminator such that the generator maximizes a discrimination error of the discriminator and the discriminator minimizes the discrimination error The anomaly detection apparatus stores, while the training is being performed, a state of the generator that is half-trained and satisfies a pre-set condition, and retrains the discriminator by using an image generated by the half-trained generator that has the stored state.

An estimation method implemented by a computer, the estimation method includes: executing learning processing by training an autoencoder with a data group corresponding to a specific task; calculating a degree of compression of each part regarding data included in the data group by using the trained autoencoder; and estimating a common part with another piece of data included in the data group regarding the data corresponding to the specific task based on the calculated degree of compression of each part.

Estimation apparatus, estimation method, and non-transitory computer-readable storage medium for storing estimation program

A learning apparatus causes a first supervised learning model, which receives feature data generated from input data having data items with which a first label and a second label are associated and outputs a first estimation result, to learn such that the first estimation result is close to the first label. The learning apparatus causes a second supervised learning model, which receives the feature data and outputs a second estimation result, to learn such that the second estimation result is close to the second label. The learning apparatus causes a feature extractor, which generates the feature data from the input data, to learn so as to facilitate recognition of the first label and suppress recognition of the second label.

Non-transitory computer-readable recording medium, learning method, and learning apparatus

An object detection device extracts feature for input data utilizing an encoder, the input data including labeled data and unlabeled data and detects object in each of the input data, utilizing an object detector. The object detection device generates region data for each of the input data, each of the region data corresponding to the detected object and generates restoration data from the region data and meta-information related to the detected object for each of the input data utilizing a decoder corresponding to the encoder. The object detection device executes learning of the encoder and the object detector based on a result detected by the object detector and a label associated with the input data, when the input data is labeled data. The object detection device executes learning of the encoder, the object detector, and the decoder, based on the input data and the restoration data.

Computer-readable recording medium, training method, and object detection device

A processor obtains a table that contains numerical values or character strings in its cells. The processor then replaces each numerical value with a first constant value, and each character string with a second constant value. The two constant values have opposite signs. The processor generates area datasets each including first to third rectangular areas. The right side of the second rectangular area coincides with the left side of the first rectangular area. The bottom side of the third rectangular area coincides with the top side of the first rectangular area. With respect to each generated area dataset, the processor compares a sum of first and second constant values in the first rectangular area with a sum of first and second constant values in the second and third rectangular areas. The processor outputs at least one of the area datasets according to the comparison result.

Growing community of inventors

Kawasaki, Japan

Kento Uemura