Panasonic Liquid Crystal Display Co., Ltd.

Nec Corporation

Semiconductor Energy Laboratory Co., Ltd.

Hitachi Displays, Ltd.

Japan Display Inc.

Ricoh Company, Ltd.

Jamco Corporation

Canon Kabushiki Kaisha

Masato Ishii

Hajime Akimoto

Naruhiko Kasai

Tohru Kohno

Mitsuhide Miyamoto

Jun Koyama

Yutaka Shionoiri

Tomoaki Atsumi

Shunpei Yamazaki

Yoshiyuki Kurokawa

Takayuki Ikeda

Takeshi Osada

Kei Takahashi

Atsushi Sato

Masahiro Ishii

Junichi Maruyama

Yoshihisa Ooishi

Toshikazu Koudo

Makoto Okamoto

Goki Toshima

Hidefumi Ishibashi

Devendra Dhaka

Masaaki Kitajima

Hidetomo Kobayashi

Takuro Ohmaru

Konami Izumi

Hiroyuki Kawamoto

Takeharu Tone

Yasuyuki Takahashi

Satoshi Ohkawa

Yasunobu Shirata

Atsushi Togami

Shuji Kimura

Akira Murakata

Tomoyuki Yoshida

Takanori Ito

Taira Matsuoka

Akira Kataoka

Hiromitsu Shimizu

Toshiya Hikita

Toshimi Yamamura

Takumi Nozawa

Takuroh Naitoh

Yukihiko Tamura

Takashi Takenouchi

Masashi Sugiyama

A data conversion learning apparatus includes a data conversion unit that performs data conversion of source data and target data, a first deduction unit that deduces data of a non-appearing class on the basis of a domain certainty factor acquired by a domain identification using converted data, a second deduction unit that deduces data of a non-appearing class on the basis of a class certainty factor acquired by a class identification using converted data, a class identification learning unit that performs machine learning for class identification using the data of the non-appearing class deduced by the first deduction unit and the source data and the target data which are inputs, and a domain identification learning unit that performs machine learning for domain identification using the data of the non-appearing class deduced by the second deduction unit and the source data and the target data which are inputs.

Data conversion learning apparatus, pattern recognition device, data conversion learning method, and recording medium

The information processing apparatus () of the example embodiment 1 includes an acquisition unit (), a modeling unit (), an output unit (). The acquisition unit () acquires a plurality of trajectory data. The trajectory data represents a time-sequence of observed positions of an object. The modeling unit () assigns one of groups for each trajectory data. The modeling unit () generates a generative model for each group. The generative model represents trajectories assigned to the corresponding group by a common time-sequence of velocity transformations. The velocity transformation represents a transformation of velocity of the object from a previous time frame, and is represented using a set of motion primitives defined in common for all groups. The output unit () outputs the generated generative models.

Information processing apparatus, and control method

A large amount of training data is typically required to perform deep network leaning, making it difficult to achieve using a few pieces of data. In order to solve this problem, the neural network device according to the present invention is provided with: a feature extraction unit which extracts features from training data using a learning neural network; an adversarial feature generation unit which generates an adversarial feature from the extracted features using the learning neural network; a pattern recognition unit which calculates a neural network recognition result using the training data and the adversarial feature; and a network learning unit which performs neural network learning so that the recognition result approaches a desired output.

Neural network learning device, method, and program

A neural network learning deviceis equipped with: a determination modulethat determines the size of a local region in learning informationwhich is to be learned by a neural networkcontaining multiple layers, said determination being made for each layer, on the basis of the structure of the neural network; and a control modulethat, on the basis of size of the local region as determined by the determination module, extracts the local region from the learning information, and performs control such that the learning of the learning information represented by the extracted local region by the neural networkis carried out repeatedly while changing the size of the extracted local region, and thus, a reduction in the generalization performance of the neural network can be avoided even when there is little learning data.

Neural network learning device, neural network learning method, and recording medium on which neural network learning program is stored

Provided is a search system which is configured to search for a registered vector being similar to an input vector among a plurality of registered vectors, on the basis of a degree of similarity between an input vector and a registered vector. The search system includes a partial similarity calculation unit that calculates a degree of partial similarity which is the degree of similarity concerning some of one or more dimensions of the input vector and the registered vector, a limit calculation unit that calculates, on the basis of the degree of partial similarity, an upper limit of the degree of similarity that is expected when the degree of similarity is calculated, and a rejection decision unit that decides, on the basis of the upper limit of the degree of similarity, whether or not to reject the registered vector from a candidate for a search result.

Search system, search method and program recording medium

The information processing apparatus () of the example embodiment 1 includes an acquisition unit (), a clustering unit (), a transformation unit () and modeling unit (). Until a predetermined termination condition is determined, the clustering unit () repeatedly preforms: 1) optimizing the posterior parameters for clustering assignment for each data streams; 2) optimizes the posterior parameters for each determined cluster and for each time frame; 3) optimizes the posterior parameters for individual responses for each data stream; 4) optimizes the posterior parameters for latent states, via approximating the observation model through non-conjugate inference. The transformation unit () transforms the latent states into parameters of the observation model, through a transformation function. The modeling unit () generates the model data, which including all the optimized parameters of all the model latent variables, optimized inside the clustering unit ().

Information processing apparatus, method, and program

A neural network training device according to an exemplary aspect of the present invention includes: a memory that stores a set of instructions; and at least one central processing unit (CPU) configured to execute the set of instructions to: determine a regularization strength for each layer, based on an initialized network; and train a network, based on the initialized network and the determined regularization strength, wherein the at least one CPU is further configured to determine the regularization strength in such a way that a difference between magnitude of a parameter update amount calculated from a loss function and magnitude of a parameter update amount calculated from a regularization term falls within a predetermined range.

Neural network training device, neural network training method and storage medium storing program

A composite material component manufacturing method including a first thermoforming step for creating a first three-dimensional prepreg sheet by thermoforming a thermoplastic first prepreg sheet into a three dimensional shape, a laminate body creating step for creating a prepreg sheet laminate body by layering the first three-dimensional prepreg sheet and a second prepreg sheet; and a laminate body molding step for molding the prepreg sheet laminate body by applying heat and a pressing force to the prepreg sheet laminate body with a pressing device.

Method for producing composite material component and device for producing composite material component

A neural network capturing a minute pattern variation useful for recognition while maintaining robustness against a pattern variation unrelated to recognition is learned. A preprocessing unit performs, on a set of patterns being to be learned and including a specific pattern variation, a plurality of preprocesses causing different degrees of the specific pattern variation. A network structure determination unit determines, for each of the plurality of preprocesses, a network structure of a neural network having robustness according to a degree of the specific pattern variation after the preprocess. A network learning unit learns, for each of the plurality of preprocesses, the neural network with the network structure associated with the preprocess using the set of patterns after the preprocess.

Information processing device, information processing method, and recording medium

A composite material component manufacturing method includes a molding step of applying, by a pressing device, heat and pressure to a prepreg to mold the prepreg, and a transfer step of transferring the prepreg. The transfer step includes moving the prepreg together with the pressing device in a state in which a pressing force is applied to the prepreg by the pressing device.

Provided are a feature transformation device and others enabling feature transformation with high precision. The feature transformation device includes receiving means for receiving training data and test data each including a plurality of samples, optimization means for optimizing weight and feature transformation parameter based on an objective function related to the weight and the feature transformation parameter, the optimization means including weight derivation means for deriving the weight assigned to each element included in the training data and feature transformation parameter derivation means for deriving the feature transformation parameter that transforms each of the samples included in the training data or the test data, objective function derivation means for deriving a value of the objective function, the objective function derivation means including a constraint determination means for determining whether the weight satisfies a prescribed constraint and regularization means for regularizing at least one of the weight or the feature transformation parameter, and transformation means for transforming an element included in at least one of the training data or the test data based on the feature transformation parameter.

Feature transformation device, recognition device, feature transformation method and computer readable recording medium

Disclosed is a verification device and the like that suppress an erroneous determination upon determining a difference between input patterns based on a similarity to a reference pattern recorded under a specific condition. A verification deviceincludes a similarity calculation unitcalculating similarities Sbetween a set of input information xand yindicating features related to input patterns that are objects of verification and a plurality of types of reference informationindicating features related to a reference pattern to be a reference of the verification by using the set of input information xand yand the plurality of types of reference information. The calculated similarities Sare presented to an external device or a user.

Verification device and control method for verifiction device, as well as computer program

Growing community of inventors

Tokyo, Japan

Masato Ishii