Abstract: According to one embodiment, a learning method includes calculating a probability distribution indicating a distribution of a probability density or a distribution of a probability at which actions are selected, selecting a first action based on the probability distribution, causing a control target to execute the first action, receiving a reward and next observation data, calculating a probability density or a probability of the first action, correcting the reward, and updating the control parameter. The reward is corrected such that the reward increases as the probability density or probability decreases.

Abstract: An information processing device 10A includes an acquisition unit 40A, a first action-value-function specifying unit 40B, a second action-value-function specifying unit 40C, and an action determination unit 40D. The acquisition unit 40A acquires a current state of a mobile robot 20 as an exemplary device. The first action-value-function specifying unit 40B has functioning of learning a first inference model by reinforcement learning, and specifies a first action-value-function of the mobile robot 20 based on the current state and the first inference model. The second action-value-function specifying unit 40C specifies a second action-value-function of the mobile robot 20 based on the current state and a second inference model that is not a parameter update target. The action determination unit 40D determines a first action of the mobile robot 20 based on the first action-value-function and the second action-value-function.

Abstract: A magnetic resonance imaging apparatus according to an embodiment includes an MRI system and a processing circuitry. The MRI system includes a receiving coil to receive a magnetic resonance signal. The processing circuitry is configured to generate an image based on the magnetic resonance signal, the image including a plurality of pixels; calculate a feature value corresponding to a signal value of the pixel; correct the feature values based on a sensitivity of the receiving coil; and reduce noise in the image based on distribution of the corrected feature values.

Abstract: A machine learning device includes an acquisition module, a first calculation module, a second calculation module, a learning module, and an output module. The acquisition module is configured to acquire observation information including information on a speed of a control target point at a control target time. The first calculation module is configured to calculate a reward for the observation information. The second calculation module is configured to calculate a corrected discount rate obtained by correcting a discount rate of the reward in accordance with a travel distance of the control target point. The learning module is configured to learn a control policy by reinforcement learning from the observation information, the reward, and the corrected discount rate. The output module is configured to output control information including information on speed control of the control target point that is determined in accordance with the observation information and the control policy.

Abstract: A route planning device includes a memory and one or more processors coupled to the memory. The one or more processors are configured to: calculate a tentative route passing through a plurality of tour points disposed in a virtual space that is acquired by removing an obstacle from a space including the obstacle; and derive a route with one or more via points added around an interference point between the obstacle included in the space and the tentative route with a calculation accuracy corresponding to a precision of via point calculation.

Abstract: According to an embodiment, a learning device includes one or more hardware processors configured to: acquire a current state of a device; learn a reinforcement learning model, and determine a first action of the device on the basis of the current state and the reinforcement learning model; determine a second action of the device on the basis of the current state and a first rule; and select one of the first action and the second action as a third action to be output to the device according to a progress of learning of the reinforcement learning model.

Abstract: A control device according to the embodiment includes a deciding unit, a reward generating unit, a simulating unit, and a next-state generating unit. The deciding unit decides on an action based on the state for the present time step. The reward generating unit generates reward based on the state for the present time step and the action. According to a simulated state for the present time step set based on the state for the present time step and according to the action, the simulating unit generates a simulated state for the next time step. The next-state generating unit generates the state for the next time step according to the state for the present time step, the action, and the simulated state for the next time step.

Abstract: According to one embodiment, a learning method, comprises receiving a first signal including a previous auxiliary variable value, previous action information regarding a previous action, or a set of previous scores, receiving current sensor data, selecting a current action of the control target based on the first signal, the current sensor data, and a parameter for obtaining a score from sensor data, causing the control target to execute the current action, receiving next sensor data and a reward, and updating the parameter based on the current sensor data, current action information regarding the current action, the next sensor data, and the reward. A degree of selecting a previous action as the current action is increased.

Abstract: A magnetic resonance imaging apparatus according to an embodiment includes an MRI system and a processing circuitry. The MRI system includes a receiving coil to receive a magnetic resonance signal. The processing circuitry is configured to generate an image based on the magnetic resonance signal, the image including a plurality of pixels; calculate a feature value corresponding to a signal value of the pixel; correct the feature values based on a sensitivity of the receiving coil; and reduce noise in the image based on distribution of the corrected feature values.

Abstract: An information processing device includes processing circuitry. The processing circuitry is configured to acquire one or more pieces of first state information representing a state of each of one or more second subjects related to a first subject to be a subject of inference at first time, and one or more pieces of second state information representing a state of each of the one or more second subjects at second time; and generate learning data for use in reinforcement learning of a machine learning model for use in inference. The learning data includes the first state information at least part of which is replaced with any of the one or more pieces of the second state information, and the second state information at least part of which is replaced with any of the one or more pieces of the first state information.

Abstract: According to one embodiment, a robot motion planning device includes processing circuitry. The processing circuitry receives observation information obtained by observing at least part of a movable range of a robot. The processing circuitry determines, in a case where first observation information is received, a target position to which the robot is to make a motion, using an action-value function and the first observation information. The processing circuitry receives measurement information obtained by measuring a state of the robot, calculates a difference corresponding to the first observation information, using the measurement information, and determines a motion plan of a force-controlled motion of the robot, based on the target position and the difference.

Abstract: A magnetic resonance imaging apparatus according to an embodiment includes an MRI system and a processing circuitry. The MRI system includes a receiving coil to receive a magnetic resonance signal. The processing circuitry is configured to generate an image based on the magnetic resonance signal, the image including a plurality of pixels; calculate a feature value corresponding to a signal value of the pixel; correct the feature values based on a sensitivity of the receiving coil; and reduce noise in the image based on distribution of the corrected feature values.

Abstract: According to an embodiment, a drive control device includes a generation unit configured to generate autonomous driving control information to control a behavior of a mobile object using autonomous driving; a prediction unit configured to predict a behavior of the mobile object when switching from the autonomous driving to manual driving; a determination unit configured to determine a difference between the behavior of the mobile object controlled by the autonomous driving control information and the behavior of the mobile object when the switching to the manual driving is made; an output control unit configured to output information that prompts a driver of the mobile object to select the autonomous driving or the manual driving, when the difference is present; and a power control unit configured to control a power unit of the mobile object using the autonomous driving or the manual driving.

Abstract: An information processing device according to an embodiment includes one or more hardware processors. The processors generate a plurality of nodes at positions corresponding to an operation indicated by an avoidance pattern to avoid a first object on a first trajectory based on one or more avoidance patterns indicating one or more operations of a mobile object for avoiding an object. The processors search for a trajectory candidate whose moving cost is smaller than that of another trajectory candidate among a plurality of trajectory candidates connecting a plurality of nodes for each avoidance pattern. The processors select a trajectory candidate whose moving cost is smaller than that of another trajectory candidate from among one or more trajectory candidates searched for each avoidance pattern.

Abstract: According to an embodiment, a drive control device configured to calculate lane attribute information including at least one of a lane recommendation degree of each lane included in lane information on a road to be traveled, a propriety of traveling each lane, and a target speed in each lane, based on own vehicle information and second vehicle information including position information and speed information on an own vehicle and a second vehicle present at a periphery of the own vehicle, route information, and map information; and determine at least one of a travel lane and a speed of the own vehicle within a range in which safety is guaranteed, using a machine learning model that receives the own vehicle information, the second vehicle information, the route information, the map information, and the lane attribute information, and outputs at least one of a travel lane and a speed.

Abstract: An image processing apparatus includes processing circuitry configured: to obtain a plurality of images taken so as to include a target site of a subject in temporal phases; and to calculate an index indicating a state of an adhesion at a boundary between a first site of the subject corresponding to a first region and a second site of the subject corresponding to a second region, by using classification information used for classifying each of pixels into one selected from between a first class related to the first region and a second class related to a second region positioned adjacent to the first region in a predetermined direction, on a basis of mobility information among the images in the temporal phases with respect to the pixels in the images that are arranged in the predetermined direction across the boundary between the first region and the second region of the images.

Abstract: An ultrasound diagnosis apparatus according to an embodiment includes processing circuitry. The processing circuitry obtains time-series data having complex values based on a reflected wave of an ultrasound wave transmitted by an ultrasound probe and calculates an expansion coefficient in a case in which the obtained time-series data is expressed as a linear sum of a plurality of mathematical functions, the time-series data having, as an argument, a first parameter related to time. The plurality of mathematical functions are mathematical functions that are possible to be generated on a basis of a function family that has, as arguments, the first parameter and a second parameter different from the first parameter.

Abstract: A controller includes one or more processors. The processors acquire first state information indicating a state of an object to be gripped by a robot and second state information indicating a state of a transportation destination of the object. The processors input the first state information and the second state information to a first neural network, and obtain, from output of the first neural network, first output information including a first position indicating a position of the robot and a first posture indicating a posture of the robot when the robot grips the object, and a second position indicating a position of the robot and a second posture indicating a posture of the robot at the transportation destination of the object. The processors control operation of the robot on the basis of the first output information.

Abstract: According to one embodiment, a learning method, comprises receiving a first signal including a previous auxiliary variable value, previous action information regarding a previous action, or a set of previous scores, receiving current sensor data, selecting a current action of the control target based on the first signal, the current sensor data, and a parameter for obtaining a score from sensor data, causing the control target to execute the current action, receiving next sensor data and a reward, and updating the parameter based on the current sensor data, current action information regarding the current action, the next sensor data, and the reward. A degree of selecting a previous action as the current action is increased.

Abstract: According to an embodiment, a network training device includes a first training unit that trains a first network that converts an input signal to a first signal, a second training unit that trains a second network that converts the first signal to a second signal, and a third training unit that trains a third network that converts the second signal to an output signal. The first training unit trains the first network as an encoder of a first autoencoder. The second training unit trains the second network by backpropagation by using a second signal for training corresponding to the first signal for training as supervised data. The second signal for training is generated by an encoder of a second autoencoder that encodes a third signal for training into the second signal for training, and decodes the second signal for training into the third signal for training.