Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: The information processing apparatus (2000) of the example embodiment 1 includes an acquisition unit (2020), a clustering unit (2040), a transformation unit (2060) and modeling unit (2080). Until a predetermined termination condition is determined, the clustering unit (2040) 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 (2060) transforms the latent states into parameters of the observation model, through a transformation function. The modeling unit (2060) generates the model data, which including all the optimized parameters of all the model latent variables, optimized inside the clustering unit (2040).

Abstract: 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.

Abstract: The information processing apparatus (2000) of the example embodiment 1 includes an acquisition unit (2020), a modeling unit (2040), an output unit (2080). The acquisition unit (2020) acquires a plurality of trajectory data. The trajectory data represents a time-sequence of observed positions of an object. The modeling unit (2040) assigns one of groups for each trajectory data. The modeling unit (2040) 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 (2060) outputs the generated generative models.

Abstract: A fuel heater including an engine that is driven by combustion of air-fuel mixture including air and fuel supplied to a combustion chamber within a cylinder, a battery that stores electricity, and a motor that drives the engine by the electricity supplied from the battery, the fuel heater includes a fuel heating portion heating the fuel with the electricity supplied from the battery, and a controller performing one of a first control by increasing the amount of electricity supplied from the battery to the fuel heating portion and a second control by increasing heating time of the fuel by the fuel heating portion for a time period until the engine starts in a case where a battery charge remaining of the battery is equal to or smaller than a remaining threshold value at a start of the engine.

Abstract: An air intake apparatus of an internal combustion engine includes a port portion into which fuel injected form an injection opening of an injector is introduced, an intake passage provided at an inner side of the port portion to flow an air-fuel mixture including the fuel and air, the air-fuel mixture being supplied to a cylinder provided at the internal combustion engine, and a port heater provided along an inner surface of the port portion to vaporize the fuel introduced into the intake passage. The port heater includes regions with different heat generation amounts from each other in accordance with a distribution of an adhesion amount of the fuel injected from the injection opening of the injector to the inner surface of the port portion.

Abstract: An air intake apparatus for an internal combustion engine includes an outer port member facing an inner surface of a suction port, an inner port member arranged inside the outer port member, and a heater arranged inside the inner port member. The inner port member is stacked on an outside of the heater in a direction orthogonal to an intake flow direction of the suction port, and is configured to insulate heat from the heater.

Abstract: 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.

Abstract: The information processing apparatus (2000) of the example embodiment 1 includes an acquisition unit (2020), a clustering unit (2040), a transformation unit (2060) and modeling unit (2080). Until a predetermined termination condition is determined, the clustering unit (2040) 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 (2060) transforms the latent states into parameters of the observation model, through a transformation function. The modeling unit (2060) generates the model data, which including all the optimized parameters of all the model latent variables, optimized inside the clustering unit (2040).

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: A neural network learning device 20 is equipped with: a determination module 22 that determines the size of a local region in learning information 200 which is to be learned by a neural network 21 containing multiple layers, said determination being made for each layer, on the basis of the structure of the neural network 21; and a control module 25 that, on the basis of size of the local region as determined by the determination module 22, extracts the local region from the learning information 200, and performs control such that the learning of the learning information represented by the extracted local region by the neural network 200 is 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.

Abstract: An air intake apparatus for an internal combustion engine, the air intake apparatus includes: an air intake apparatus main body portion introducing air into a cylinder; a port portion provided integrally with a downstream side end portion of the air intake apparatus main body portion and inserted into an air intake port in a cylinder head; an air intake passage formed inside the air intake apparatus main body portion and the port portion, and through which an air-fuel mixture containing air and fuel flows; an injector provided in the air intake apparatus main body portion and introducing the fuel into the air intake passage; and a heater heating the fuel introduced by the injector. The injector is disposed at a position where the fuel is capable of being injected into the heater.

Abstract: 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.

Abstract: This prediction model preparation device is provided with: a calculation means which calculates, from a datum in which a sample and a label are associated with each other, an importance level according to the difference between a first possibility that an event influencing the sample occurs in a source domain and a second possibility that the event occurs in a target domain; and a preparation means which constructs prepares a prediction model relating to the target domain by calculating association between the sample and the label included in the datum to which the importance level is added.

Abstract: A substrate processing system is disclosed which includes a processing chamber comprising a susceptor having a first surface and a second surface opposite to the first surface, a groove formed in the first surface adjacent to a perimeter thereof, and a substrate support structure including a plurality of carrier lift pins, each of the plurality of carrier lift pins movably disposed in an opening formed from the second surface to the first surface, wherein the opening is recessed from the groove.

Abstract: A learning device according to the present invention includes, in semi-supervised learning using domain information: a memory; and a processor. The processor performs operations. The operations includes: including a first neural network outputting data after predetermined conversion by using first data including the domain information and second data not including the domain information, a second neural network outputting a result of predetermined processing by using data after the conversion, and a third neural network outputting a result of domain discrimination by using data after the conversion; calculating a first loss being a loss of the domain discrimination; calculating a second loss being an unsupervised loss; calculating a third loss in the predetermined processing; and modifying a parameter of each of the first neural network to the third neural network in such a way as to decrease the second loss and the third loss and increase the first loss.