Abstract: According to one embodiment, a learning apparatus includes processing circuitry. The processing circuitry generates a plurality of pieces of partial data from a mini-batch of learning data used for a plurality of learning processes for learning of a parameter of a neural network using an objective function, calculates a partial gradient that is a gradient related to the parameter of the objective function for each of the pieces of partial data, and updates the parameter based on an average value of the plurality of partial gradients corresponding to the pieces of partial data and a variance for the partial gradients.

Abstract: An OOD data detection apparatus includes: an obtainment unit that obtains monitoring target data; an intermediate output calculation unit that calculates an intermediate output by applying a trained model to the monitoring target data; a projected-component calculation unit that calculates a projected component of the intermediate output to a parameter constituting the trained model; and a discrimination unit that discriminates as to whether the monitoring target data is OOD data based on the projected component.

Abstract: According to one embodiment, a machine learning model evaluation system includes processing circuitry. The processing circuitry inputs used data used for training a machine learning model and target data to be input to the machine learning model for prediction. The processing circuitry calculates first statistical information from an output which the machine learning model produces with respect to the used data. The processing circuitry calculates second statistical information from an output which the machine learning model produces with respect to the target data. The processing circuitry evaluates reliability of the machine learning model, based on a difference or a rate of change between the first and second statistical information and on a threshold value.

Abstract: According to one embodiment, an importance calculation apparatus includes a processing circuit. The processing circuit obtains data in which samples each including values regarding a plurality of explanatory variables and one response variable are arranged in a predetermined order. The processing circuit generates first data in which a first correspondence between the values of the plurality of explanatory variables and the values of the response variable is randomized between the samples in the data, and second data in which a correspondence between the values of at least one target explanatory variable among the plurality of explanatory variables and the values of the response variable is restored to the first correspondence in the first data.

Abstract: A health support apparatus includes a processor including hardware. The processor accepts input of a first factor that is directly controlled by improving a lifestyle habit of a person subjected to a medical checkup and a second factor that is not directly controlled by improving a lifestyle habit of the person. The processor generates a lifestyle habit combination pattern. The processor calculates change amounts of the first factor and the second factor corresponding to the combination pattern. The processor predicts a disease risk value representing a disease risk of a disease of the person based on at least the change amount of the second factor.

Abstract: A learning device includes one or more processors. The processors generate a plurality of pieces of learning data to be used in a plurality of learning processes, respectively, to learn a parameter of a neural network using an objective function. The processors calculate a first partial gradient using a partial data and the parameter added with noise, with respect to at least a part of the learning data out of the plurality of pieces of learning data. The partial data is obtained by dividing the learning data. The first partial gradient is a gradient of the objective function relating to the parameter for the partial data. The noise is calculated based on a second partial gradient calculated for another piece of the learning data. The processors update the parameter using the first partial gradient.

Abstract: According to one embodiment, a trait prediction model generation apparatus generates a plurality of first trait prediction models for each of a plurality of populations, based on summary statistics and inter-polymorphism correlated information. The apparatus generates a second trait prediction model for a specific one of the populations based on regularized regression of the first trait prediction models of each of the populations using a plurality of data sets including single-nucleotide polymorphism data and a trait value.

Abstract: A health support apparatus includes a processor including hardware. The processor accepts input of a first factor that is directly controlled by improving a lifestyle habit of a person subjected to a medical checkup and a second factor that is not directly controlled by improving a lifestyle habit of the person. The processor calculates change amounts of the first factor and the second factor. The processor predicts a disease risk value representing a disease risk of a disease of the person based on at least the change amount of the second factor.

Abstract: A machine learning model compression system according to an embodiment includes one or more hardware processors configured to: select a layer of a trained machine learning model in order from an output side to an input side of the trained machine learning model; calculate, in units of an input channel, a first evaluation value evaluating a plurality of weights included in the selected layer; sort, in ascending order or descending order, the first evaluation values each calculated in units of the input channel; select a given number of the first evaluation values in ascending order of the first evaluation values; and delete the input channels used for calculation of the selected first evaluation values.

Abstract: According to one embodiment, a healthcare support system includes a memory and a hardware processor connected to the memory. The hardware processor predicts a risk value of a disease based on medical checkup data for a medical examinee. The hardware processor sets a reduction target for the risk value of the disease, and sets a plurality of second factors constituting search targets among a plurality of first factors relating to the disease and a search range for each of the second factors. The hardware processor searches, by using a predetermined search method, in the search range for each of the second factors, for a target value candidate of each of the second factors so that the risk value of the disease is brought close to the reduction target.

Abstract: According to an embodiment, a machine learning model compression system includes a memory and a hardware processor. The hardware processor is coupled to the memory and configured to: analyze an eigenvalue of each layer of a machine learning model by using a data set and the machine learning model, the machine learning model having been learned based on the data set; determine a search range of a compressed model based on a count of eigenvalues, each of which is used for calculating a first value and causes the first value to exceed a predetermined threshold; select a parameter for determining a structure of the compressed model included in the search range; generate the compressed model by using the parameter, and judge whether the compressed model satisfies one or more predetermined restriction conditions or not.

Abstract: A learning device includes one or more processors. The processors generate a plurality of pieces of learning data to be used in a plurality of learning processes, respectively, to learn a parameter of a neural network using an objective function. The processors calculate a first partial gradient using a partial data and the parameter added with noise, with respect to at least a part of the learning data out of the plurality of pieces of learning data. The partial data is obtained by dividing the learning data. The first partial gradient is a gradient of the objective function relating to the parameter for the partial data. The noise is calculated based on a second partial gradient calculated for another piece of the learning data. The processors update the parameter using the first partial gradient.

Abstract: A monitoring system includes storage, and one or more processors. The storage stores at least one of first output data that is obtained from a learning model, or first statistical information that is obtained from the first output data. The processors calculate a degree of abnormality indicating a degree of change in statistical information of second output data with respect to the first statistical information, or a degree of change in the statistical information of the second output data with respect to second statistical information. The processors determine whether or not there is occurrence of an abnormality in the learning model, on the basis of the degree of abnormality. The processors output information indicating occurrence of the abnormality, in a case where occurrence of the abnormality is determined.

Abstract: According to one embodiment, in nth (n is a natural number) processing, a first node calculates a first gradient to update a first weight and a second node calculates a second gradient to update the first weight. In mth (m is a natural number) processing, a third node calculates a third gradient to update a third weight and a fourth node calculates a fourth gradient to update the third weight. If the calculation by the first and second nodes is faster than the calculation by the third and fourth nodes, in n+1th processing, a second weight updated from the first weight is further updated using the first and second gradients, and, in m+1th processing, a fourth weight updated from the third weight is further updated using the first to fourth gradients.

Abstract: According to one embodiment, an electronic apparatus includes a memory, and a processor. The processor is connected to the memory to acquire display information including an object and, when an amount of depth or pop-out of the object to be displayed in space using the display information including the object exceeds an amount of depth or pop-out set displayable to a first display device capable of stereoscopic display at a time of stereoscopically displaying the display information on the first display device, to display the exceeding area in a display form different from a display form included in the display information.

Abstract: According to one embodiment, a server is included in a system which also includes a second server and a third server. The server also configured to specify, from a search range of the parameters, a first combination of first initial parameters and a second combination of second initial parameters, using a search method based on a uniform distribution, and to specify, from a search range of the parameters, a third combination of third parameters, based on the first and second learning results and using a search method based on a probability distribution.

Abstract: According to one embodiment, an electronic apparatus includes a memory, and a processor. The processor is connected to the memory to acquire display information including an object and, when an amount of depth or pop-out of the object to be displayed in space using the display information including the object exceeds an amount of depth or pop-out set displayable to a first display device capable of stereoscopic display at a time of stereoscopically displaying the display information on the first display device, to display the exceeding area in a display form different from a display form included in the display information.

Abstract: In an embodiment, an electronic device includes circuitry configured to automatically execute exposures at a photographing range including at least a first region and a second region, with different focuses by a camera, and acquire first images generated by the exposures, and display a second image on a display based on the first images. A number of exposures at the photographing range of a first photographing and a second photographing are different. The first photographing is a case when a difference between a distance from the camera to the first subject and a distance from the camera to the second subject is greater than or equal to a first value. The second photographing is a case when the difference is smaller than the first value.

Abstract: According to one embodiment, an electronic apparatus in which user can see through at least a transparent part of a first display area when the electronic apparatus is worn on a body of the user is provided. The electronic apparatus includes a camera configured to take an image of surroundings comprising a region which the user cannot see through at least a transparent part of the first display area when the electronic apparatus is worn on a body of the user, and circuitry configured to perform controlling display of the first display area by using the image of surroundings.

Abstract: In an embodiment, an electronic device includes circuitry configured to automatically execute exposures at a photographing range including at least a first region and a second region, with different focuses by a camera, and acquire first images generated by the exposures, and display a second image on a display based on the first images. A number of exposures at the photographing range of a first photographing and a second photographing are different. The first photographing is a case when a difference between a distance from the camera to the first subject and a distance from the camera to the second subject is greater than or equal to a first value. The second photographing is a case when the difference is smaller than the first value.