Abstract: An inferring device includes one or more memories; and one or more processors. The one or more processors are configured to input information on each atom in an atomic system into a second model to infer a difference between energy based on a first-principles calculation corresponding to the atomic system and energy of an interatomic potential function corresponding to the atomic system.

Abstract: With respect to an inference method performed by at least one processor, the method includes inputting, by the at least one processor, into a learned model, non-processed object image data of a second object and data related to a second process for the second object, and inferring, by the at least one processor using the learned model, processed object image data of the second object on which the second process has been performed. The learned model has been trained so that an output obtained in response to non-processed object image data of a first object and data related to a first process for the first object being input approaches processed object image data of the first object on which the first process has been performed.

Abstract: A fitting structure for an electrical connection part, includes a case body with an opening, and a cap connected to the case body turnably about a center of turning which extends substantially perpendicular to an insertion direction of an external connection terminal connected to a connection terminal housed in the case body. The case body includes a fitting portion around the opening, and a first engagement piece extending outside from the fitting portion. The cap includes a second engagement piece extending inside to engage with the first engagement piece. An extension of at least one of the first engagement piece or second engagement piece decreases in length in the direction of the center of turning, toward an end of the extension, and/or includes chamfers on the both sides of the middle position of the extension in the direction of the center of turning.

Abstract: An inferring device includes one or more memories and one or more processors. The one or more processors input a vector relating to an atom into a first network which extracts a feature of the atom in a latent space from the vector relating to the atom, and infer the feature of the atom in the latent space through the first network.

Abstract: A fitting structure for an electrical connection part, includes a case body with an opening, and a cap connected to the case body turnably about a center of turning which extends substantially perpendicular to an insertion direction of an external connection terminal connected to a connection terminal housed in the case body. The case body includes a fitting portion around the opening, and a first engagement piece extending outside from the fitting portion. The cap includes a second engagement piece extending inside to engage with the first engagement piece. An extension of at least one of the first engagement piece or second engagement piece decreases in length in the direction of the center of turning, toward an end of the extension, and/or includes chamfers on the both sides of the middle position of the extension in the direction of the center of turning.

Abstract: With respect to an inference method performed by at least one processor, the method includes inputting, by the at least one processor, into a learned model, non-processed object image data of a second object and data related to a second process for the second object, and inferring, by the at least one processor using the learned model, processed object image data of the second object on which the second process has been performed. The learned model has been trained so that an output obtained in response to non-processed object image data of a first object and data related to a first process for the first object being input approaches processed object image data of the first object on which the first process has been performed.

Abstract: With respect to an inference method performed by at least one processor, the method includes inputting, by the at least one processor, into a learned model, second non-processed image data and second parameter data of a simulator, and inferring, by the at least one processor using the learned model, second processed image data. The learned model has been trained so that first processed image data, obtained as an output in response to first non-processed image data and first parameter data of the simulator for the first non-processed image data being input, approaches first simulator processed image data, obtained as a result of the simulator for the first non-processed image data by using the first parameter data.

Abstract: A seal structure that secures sufficient sealing function even under a situation that causes a tilt of a sealing member in the seal structure. The seal structure includes a case, a cover, and a sealing member on which pressure acts while being sandwiched between the case and the cover. The sealing member includes a main body, a first protrusion protruding from the main body toward the case, and a second protrusion protruding from the main body toward the cover. The case includes a first recess that comes into contact with the first protrusion, and the cover includes a second recess that comes into contact with the second protrusion. The first protrusion and the first recess are different in shape. Furthermore, the second protrusion and the second recess are different in shape.

Abstract: A material structure analysis scheme for using machine learning to predict a general structure of an arbitrary material is provided. One aspect of the present disclosure relates to a material structure analysis method, including acquiring, by one or more processors, structural data representing a structure of a material and spectral data representing a spectrum of a material, inputting, by the one or more processors, the structural data to a first neural network to acquire a structural feature from the first neural network, inputting, by the one or more processors, the spectral data to a second neural network to acquire a spectral feature from the second neural network, and determining, by the one or more processors, a degree of coincidence between the material corresponding to the structural data and the material corresponding to the spectral data based on the structural feature and the spectral feature.

Abstract: Techniques for improving simulation accuracy of a trained model are disclosed. One aspect of the present disclosure relates to a training apparatus, including: a memory storing a training model including an encoder unit having multiple convolutional layers and a decoder unit having multiple corresponding deconvolutional layers; and one or more processors that are configured to: calculate a feature indicative of a dependency of data in a predetermined direction based on a data set output from a N-th convolutional layer (N is a positive integer) in the encoder unit; and input the calculated feature to a N-th deconvolutional layer in the decoder unit.