Abstract: Provided are an analysis device, an analysis method, and a program capable of easily identifying a factor of a prediction error in prediction using a prediction model on the basis of various viewpoints. An analysis device (1) includes: a metric evaluation unit (2) that calculates and evaluates a plurality of types of metrics with respect to a prediction model, data of explanatory variables used in the prediction model, or data of target variables used in the prediction model; and a factor identification unit (3) that identifies a factor of an error in prediction by the prediction model according to a combination of evaluation results of the plurality of types of metrics.

Abstract: Predictively robust models are trained by embedding a distribution of each temporal data set among a plurality of temporal data sets into a feature vector, predicting a future feature vector of a distribution of a future data set, based on the feature vector of each temporal data set among a plurality of temporal data sets, creating the future data set from the future feature vector, perturbing the future data set to produce a plurality of perturbed future data sets, and training a learning function using the future data set and each perturbed future data set to produce a model.

Abstract: A method of training an image recognition model includes masking a first region of a first image with a first portion of a second image to define a mixed image, wherein the first image is different from the second image, and a location of the first region in the first image corresponds to a location of the first portion in the second image. The method further includes performing masked global average pooling (GAP) on both the mixed image. The method further includes generating a first classification score for the first image and a second classification score for the second image based on the masked GAP of the mixed image.

Abstract: A control customization system 80 customizes a plant control. A profiler 81 predicts actions of a user depending on situations of the plant or the user. A planner 82 determines an appropriate set of objectives which represent tasks desired by the user, and objective terms representing elements for controlling the plant so as to realize the objectives, and tunes the objective terms based on predictions of the profiler 81.

Abstract: Forward compatible models are obtained by operations including training a learning function with a current training data set to produce a first model, the current training data set including a plurality of samples, generating a plurality of prospective models, each prospective model based on a variation of one of the current training data set or the first model, adjusting a plurality of sample weights based on output of one or more prospective models among the plurality of prospective models in response to input of the current training data set, and retraining the learning function with the current training data set and the plurality of sample weights to produce a second model.

Abstract: Distributionally robust models are obtained by operations including training, according to a loss function, a first learning function with a training data set to produce a first model, the training data set including a plurality of samples. The operations may further include training a second learning function with the training data set to produce a second model, the second model having a higher accuracy than the first model. The operations may further include assigning an adversarial weight to each sample among the plurality of samples set based on a difference in loss between the first model and the second model. The operations may further include retraining, according to the loss function, the first learning function with the training data set to produce a distrtibutionally robust model, wherein during retraining the loss function further modifies loss associated with each sample among the plurality of samples based on the assigned adversarial weight.

Abstract: A model estimation system estimates a model of a system represented by an ordinary differential equation with all coefficients being non-zero, and with which input data and a state at each time can be obtained. When an order of the ordinary differential equation and input data and a state at multiple past times in the system are inputted, a model expression construction unit constructs an expression representing a model by using a first matrix that is a matrix according to the order and has only some elements as unknown elements and a second matrix that is a matrix according to the order and has only some one element as an unknown element. A model estimation unit uses input data and a state at multiple past times, to estimate the model by learning unknown elements of the first matrix and the unknown element of the second matrix.

Abstract: An expert model unit 81 generates predicted expert control actions based on an expert model which is a machine learning model trained using data collected when an expert operated a plant which is a control target or a plant of the same or similar characteristics. A transformer 82 constructs metrics or error measures involving the predicted expert control actions from the expert model unit 81 as an objective term. A combiner 83 collects different objective terms from the transformer 82 and a learner which outputs machine-learning models as objective terms and computes an optimal set of weights or combinations of the objective terms to construct an aggregated cost function for use in an optimizer.

Abstract: A vehicle control system for controlling driving of a vehicle reflecting an environment and a characteristic of a user, while suppressing increase in learning time, is provided. The vehicle control system includes classification means for classifying, by using one or more attributes selected from accumulation means for accumulating data including attributes relating to driving of a vehicle, driving properties included in the data, learning means for learning a model representing the driving property, for each of types that are a result of classification by the classification means, and control information determination means for determining, by using the model learned for the type associated with a value of the attribute at time of driving of a control target vehicle, control information for the driving.

Abstract: A search device includes: a relationship calculation means for calculating a relationship by using a plurality of sets, each set including a parameter value and a numerical value indicating a degree of occurrence of a target event in a case of the parameter value, the relationship being a relationship between the parameter value and the numerical value; a frequency calculation means for calculating, for a plurality of bins obtained by dividing up a range that can be taken by the numerical value, a frequency at which the numerical value is included in a bin; a number setting means for performing, for at least some bins of the plurality of bins, a setting relating to a number of the parameter value such that the lower the frequency of the bin, the greater a number of the parameter value serving as calculation subjects of the numerical value, by using the frequency; and a parameter setting means for setting parameter values by the set number.

Abstract: An analysis device applies, for each of a plurality of candidates set according to a update target parameter value, the update target parameter value and the candidate to a machine learning result to acquire information, the information indicating a degree of difference of an evaluation target value in a case of the candidate with respect to an evaluation target value in a case of the update target parameter value; calculates, for each candidate, an evaluation target value in a case of the candidate, based on the degree of difference of the evaluation target values and the evaluation target value in the case of the update target parameter value; and compares the evaluation target values in a case of each of the plurality of candidates and selects a candidate from the plurality of candidates based on a result of the comparison.

Abstract: An analysis device applies, for each of a plurality of candidates for an updated parameter value set according to an update target parameter value, the update target parameter value and the candidate to a plurality of machine learning results to acquire, for each machine learning result, information indicating a degree of difference of an evaluation target value in a case of the candidate with respect to an evaluation target value in a case of the update target parameter value; calculate, for each candidate and for each machine learning result, an evaluation target value in the case of the candidate based on the degree of difference and the evaluation target value in the case of the update target parameter value; and calculate a selection index value for each candidate using a variation in the evaluation target values for each machine learning result, compare the selection index value of each candidate.

Abstract: A vehicle control system for controlling driving of a vehicle reflecting an environment and a characteristic of a user, while suppressing increase in learning time, is provided. The vehicle control system includes classification means for classifying, by using one or more attributes selected from accumulation means for accumulating data including attributes relating to driving of a vehicle, driving properties included in the data, learning means for learning a model representing the driving property, for each of types that are a result of classification by the classification means, and control information determination means for determining, by using the model learned for the type associated with a value of the attribute at time of driving of a control target vehicle, control information for the driving.

Abstract: Provided are a reference scale and dimension measurement system that make it possible to maintain accurate measurement even if the reference scale is not disposed or projected on a measurement surface.

Abstract: An ensemble control system 80 combines different types of plant control. A plurality of subcontrollers 81 output actions for the plant control based on a prediction result by a predictor. A combiner or switch 82 combines or switches actions to maximize prediction or control performance as best control action based on the actions output by each subcontroller 81. Subcontrollers 81 include at least two types of subcontrollers. A first type subcontroller is an optimization-based subcontroller which optimizes an objective function that is a cost function to be minimized for calculating actions and outputs a control action. A second type subcontroller is a prediction-subcontroller which predicts based on machine learning models and outputs a predicted action.

Abstract: A control customization system 80 customizes a plant control. A profiler 81 predicts actions of a user depending on situations of the plant or the user. A planner 82 determines an appropriate set of objectives which represent tasks desired by the user, and objective terms representing elements for controlling the plant so as to realize the objectives, and tunes the objective terms based on predictions of the profiler 81.

Abstract: Provided is a model estimation system that can estimate a discrete time state space model having controllability. The model estimation system of the present invention estimates a model of a system that is represented by an ordinary differential equation with all the coefficients being non-zero, and with which input data and a state at each time can be obtained. When an order of the ordinary differential equation and input data and a state at multiple past times in the system are inputted, a model expression construction means 22 constructs an expression representing a model by using a first matrix that is a matrix according to the order and has only some elements as unknown elements and a second matrix that is a matrix according to the order and has only some element as an unknown element. A model estimation means 23 uses input data and a state at multiple past times, to estimate the model by learning unknown elements of the first matrix and an unknown element of the second matrix in the expression.

Abstract: An information processing device for enabling acquisition of a simulation output with high precision or in a short time, as compared with the technique disclosed in PTL 1 or 2, is provided. The information processing device includes an acquisition unit and a learning unit. The acquisition unit acquires a value of an input variable used for executing a simulation, an updated value of an internal variable updated during execution of the simulation, and a value of an output variable indicating a result of the simulation. The learning unit learns an estimation model for estimating a simulation result by using the input variable and the updated internal variable acquired by the acquisition unit as explanatory variables and the output variable acquired by the acquisition unit as an objective variable.

Abstract: This information processing device is equipped with: an actual travel data acquisition means that acquires actual travel data, which is travel data obtained by the driving of a vehicle by a driver; a simulated travel data acquisition means that uses travel environment data indicating the travel environment associated with the travel, and a driver model that determines the operation of the vehicle with respect to the travel environment, to acquire simulated travel data, which is travel data obtained from a simulator that simulates the driving of the vehicle by the driver; and a comparison means that compares the values of multiple indices of the actual driving data and the values of multiple indices of the simulated travel data, and that outputs the comparison results.

Abstract: To efficiently process a programming problem including a function defined piecewise without having the differentiability and continuity of the function expressing the problem or spatial continuity as prerequisites, a non-linear programming problem processing device is provided with: a non-linear programming problem input unit; a provisional solution generation unit that produces a solution obtained in a certain region of the non-linear programming problem as a provisional solution; a solution candidate generation unit that produces a solution obtained in a nearby region of the provisional solution as a solution candidate; a provisional solution update unit that updates the solution candidate in accordance with the result of comparison of the provisional solution and the solution candidate; an end determination unit that determines the end of the process using a provisional solution improvement degree and/or the number of times of generation of the solution candidate; and a non-linear programming problem solut