Hirotaka Suzuki

TL;DR: In this article, an information processing device including a display section configured to display a first object in a virtual three-dimensional space having a depth direction of a display screen, an operation part configured to acquire an operation for moving the first object on the display screen in accordance with the acquired operation, to execute, when a region of the first objects overlaps a first overlap determination region, a first process to one or both of thefirst and second objects, and to execute when the region of an object overlaps the second overlap determination regions, a second process to either the first or the second

TL;DR: In this article, a model posture estimation section repeatedly projects to a parameter space the affin conversion parameter decided from three pairs selected at random from the candidate corresponding characteristic point pairs, defines each member of a cluster having the maximum number of members formed on the parameter space as an inlier, calculates an affin converting parameter by minimum square estimation using the inlier and outputs the model posture decided by this affIN conversion parameter.

TL;DR: In this article, a model learning means for self-organizing, on the basis of a state transition model having a state and state transition to be learned by using time series data as data in time series, an internal state from an observation signal obtained by a sensor.

TL;DR: In this paper, the authors presented an image processing system, a learning device and a method, and a program capable of easily extracting a characteristic amount used for recognition processing. But this method was not applied to a robot.

TL;DR: In this article, a learning system for self-organizationally updating the dynamics of the network on the basis of measured time-series data is presented, which includes network storage means for storing a network including a plurality of nodes, each of which holds a dynamics.