Abstract: An inference apparatus provides target data to multiple inference models to cause the inference models each derived from local learning data obtained in a different environment to perform predetermined inference to obtain an inference result from each of the inference models. The inference apparatus determines the value of each combining parameter using environment data, weights the inference result from each of the inference models using the determined value of each combining parameter, and combines the weighted inference result from each inference model together to generate an inference result in a target environment.

Abstract: An agent control device includes a movement determination unit configured to input a first observation set, obtained by observing a state of a control target agent, and to input a second observation set, obtained by observing a state of at least one other agent in a periphery of the control target agent, to a first model and to determine information regarding movement of the control target agent in accordance with an output of the first model, a change amount determination unit configured to input the first observation set and the second observation set to a second model and to determine a change amount with respect to the information regarding movement of the control target agent, and an operation control unit configured to operate the control target agent by applying the change amount determined by the change amount determination unit to the information regarding movement determined by the movement determination unit.

Abstract: This learning device comprises: a creation unit which creates a state transition model that predicts a next state of a robot on the basis of a measured robot state and a command for the robot, and a collection state transition model including a collection unit that collects the prediction results; a command generation unit which executes, for each control period, processes for inputting the measured robot state, generating candidates of the command for the robot, acquiring a robot state predicted from the robot state and the candidates of the command for the robot by using the collection state transition model 20, and generating and outputting a command for maximizing a reward corresponding to the acquired state; and a learning unit which updates the collection state transition model in order to reduce an error between a next robot state predicted in correspondence with the output command and a robot state measured in correspondence with the next state.

Abstract: A model generation apparatus trains a search module on training data pairs through machine learning to find a path fitting a recommended path indicated by true information in response to receiving an input of a training map as an input map. In the machine learning, the model generation apparatus performs, in a phase of forward propagation, an extraction operation and a selection operation, and replaces, in a phase of backpropagation, the extraction operation and the selection operation with differentiable alternative operations and differentiates the alternative operations to compute approximate gradients corresponding to differentiation calculations for the extraction operation and the selection operation.

Abstract: A prediction model (1) includes a first module (M1) that calculates, for each of a plurality of objects (xi) in a dataset (x), an index value (vi) corresponding to a combination of the object (xi) and attribute information (a) using a neural network, and a second module (M2) that calculates a prediction result (y) of an operation to be performed by a user by performing a predetermined process on a plurality of index values (v1, . . . , vN) obtained from the first module (M1) and corresponding to the respective plurality of objects (x1, . . . , xN).

Abstract: Provided is a technique for generating a movement plan rapidly and at a relatively light memory load, even for a complicated task, while guaranteeing executability in a real environment. A movement planning device according to one aspect of the present invention uses a symbolic planner to generate an abstract action sequence including one or more abstract actions that are arranged in the order of execution. The movement planning device: uses a motion planner to generate, from each abstract action and in the order of execution, a sequence of movements; and determines whether the generated sequence of movements can be physically executed by a robot device in the real environment.

Abstract: A model generation apparatus trains, through machine learning, a neural network module that includes an extraction operation to extract an element satisfying a predetermined condition from a set of targets. In the machine learning, the model generation apparatus performs the extraction operation in a phase of forward propagation with the neural network module, and replaces, in a phase of backpropagation, the extraction operation with a differentiable alternative operation and differentiates the alternative operation to compute an approximate gradient corresponding to differentiation for the extraction operation.

Abstract: A parameter adjustment apparatus according to one or more embodiments calculates the degrees of association between an object inference task and existing inference tasks, according to the similarity in objective between the object inference task and the existing inference tasks, and determines a plurality of object weights that constitute an object weight set according to the calculated degrees of association, from a plurality of existing weights of existing weight sets indicated by existing task information.

Abstract: A method for use with a computing device is provided. The method may include inputting an input data set into a first private artificial intelligence model generated using a first private data set and a second private artificial intelligence model generated using a second private data set. The method may further include receiving a first result data set from the first private artificial intelligence model and receiving a second result data set from the second private artificial intelligence model. The method may further include training an adaptive co-distillation model with the input data set and the first result data set. The method may further include training the adaptive co-distillation model with the input data set and the second result data set. The adaptive co-distillation model may not be trained on the first private data set or the second private data set.

Abstract: A model generation apparatus according to one or more embodiments acquires, with respect to each of learning data sets, background data for training data, and obtains a difference between the training data and the background data to generate differential data. The model generation apparatus trains an estimator so that, with respect to each of the learning data sets, a result of estimating a feature by the estimator based on the generated differential data conforms to correct answer data.

Abstract: A model generation apparatus according to one or more embodiments executes operations, with respect to each of learning data sets. The operations includes training a second estimator so that an estimation result obtained from a second estimator conforms to second correct answer data; training a coder so that an estimation result obtained from the second estimator does not conform to the second correct answer data; and training the coder and the first estimator so that an estimation result obtained from a first estimator conforms to first correct answer data. The model generation apparatus executes operation of the training the second estimator and the training the coder alternately and repeatedly.

Abstract: An integrated analysis method according to one or more embodiments may include: a step of each client apparatus executing computation for obtaining correlation between elements in local samples included in the local learning data; a step of a server apparatus acquiring results of the computation by the client apparatuses; a step of the server apparatus calculating an integration result indicating the correlation between elements of all of the local samples of all of the local learning data, by integrating the results of computation acquired from the client apparatuses; a step of the server apparatus deriving one or more principal components from the calculated integration result by performing principal component analysis; and a step of the server apparatus outputting information regarding the one or more derived principal components.

Abstract: A robot control model learning device (10) performs, by using state information indicating the state of a robot which autonomously travels to a destination in a dynamic environment as an input, reinforcement learning to obtain a robot control model for selecting and outputting a behavior in accordance with the state of the robot from among a plurality of behaviors including an intervention behavior for intervening in the environment, while using the number of times the intervention behavior has been performed as a minus reward.

Abstract: A self-position estimation model learning device (10) includes: an acquisition unit (30) that acquires, in time series, a local image captured from a viewpoint of a self-position estimation subject in a dynamic environment, and a bird's-eye view image which is captured from a location overlooking the self-position estimation subject and is synchronized with the local image; and a learning unit (32) for learning a self-position estimation model that takes the local image and the bird's-eye view image acquired in time series as input, and outputs the position of the self-position estimation subject.

Abstract: An inference apparatus provides target data to multiple inference models to cause the inference models each derived from local learning data obtained in a different environment to perform predetermined inference to obtain an inference result from each of the inference models. The inference apparatus determines the value of each combining parameter using environment data, weights the inference result from each of the inference models using the determined value of each combining parameter, and combines the weighted inference result from each inference model together to generate an inference result in a target environment.

Abstract: A data generation system according to one or more embodiments generates a first pseudo sample including a first feature of a type corresponding to an input value using a trained first generator, a second pseudo sample including a second feature of a type corresponding to an input value using a trained second generator, and a new sample including the first feature and the second feature by synthesizing the generated first pseudo sample and the generated second pseudo sample.

Abstract: A model generation apparatus according to one or more embodiments may include: a generating unit that generates data using a generation model; a transmitting unit that transmits the generated data to a plurality of trained identification models that each have acquired, by machine learning using local learning data, a capability of identifying whether given data is the local learning data, and causes the identification models to perform an identification on the data; a receiving unit that receives results of identification with respect to the transmitted data executed by the identification models; and a learning processing unit that trains the generation model to generate data that causes identification performance of at least one of the plurality of identification models to be degraded, by performing machine learning using the received results of identification.

Abstract: A model integration apparatus according to one or more embodiments may include a model collecting unit that collects trained learning models from a plurality of learning apparatuses, an integration processing unit that executes integration processing of integrating the results of machine learning reflected in an integration range set in the common portion, with respect to the trained learning models, and a model updating unit that transmits a result of the integration processing to the learning apparatuses. The model updating unit may further update the trained learning models retained by the learning apparatuses by causing the learning apparatuses to each apply the result of the integration processing to the integration range in the trained learning model.

Abstract: A method for use with a computing device is provided. The method may include inputting an input data set into a first private artificial intelligence model generated using a first private data set and a second private artificial intelligence model generated using a second private data set. The method may further include receiving a first result data set from the first private artificial intelligence model and receiving a second result data set from the second private artificial intelligence model. The method may further include training an adaptive co-distillation model with the input data set and the first result data set. The method may further include training the adaptive co-distillation model with the input data set and the second result data set. The adaptive co-distillation model may not be trained on the first private data set or the second private data set.

Abstract: A method for modeling crowd movement includes obtaining a temporal sequence of images of a physical venue and, for each of the images, subdividing the respective image into a respective set of logical pixels according to a predetermined mapping. For each logical pixel of each image, the method computes a respective crowd density representing a respective number of mobile objects per unit of area in the physical venue at the logical pixel, thereby forming a temporal sequence of crowd density maps that corresponds to the temporal sequence of images. The method then uses successive pairs of crowd density maps to train a model on spatiotemporal changes in crowd density at the physical venue. A method of predicting future crowd density maps at physical venues using a current image of the physical venue and the trained model is also disclosed.