Learn More
– Fuzzy inference models can conduct advanced inference using knowledge which is easily understood by humans. In this paper, we propose a leaning fuzzy inference model. The model can learn with experience data obtained by trial-and-error of a task. The learning of the model is executed after each trial of the task. Hence, it is expected that the achievement(More)
A fuzzy inference model for learning from experiences (FILE) is proposed. the model can learn from experience data obtained by trial-and-error of a task and it can stably learn from both experiences of success and failure of a trial. the learning of the model is executed after each of trial of the task. hence, it is expected that the achievement rate(More)
—This paper addresses the automatic generation of a typographic font from a subset of characters. Specifically, we use a subset of a typographic font to extrapolate additional characters. Consequently, we obtain a complete font containing a number of characters sufficient for daily use. The automated generation of Japanese fonts is in high demand because a(More)
We discuss two issues of video processing based on our recent results: missing data estimation and multiple motion segmentation. We first show that for a rigidly moving scene we can reliably extend interrupted feature point tracking by imposing a geometric constraint based on the affine camera modeling. For scenes of multiple motions, many techniques have(More)
Various image and video compression methods have been developed so far for data reduction. However, necessary information of an original image or video may be degraded if the image is highly compressed without considering the importance of each region in the image. In this paper, we propose a method to detect regions that are important for humans in an(More)
In this paper, we proposed an adaptive and sequential learning network model (ASLN model). ASLN model is a neural network model for sequential learning of temporal sequences under restriction of memory capacity. The proposed model can successively learn elements and its transitions from input data given to the model under restriction of memory capacity. The(More)
1. [1, 2] () () MOSAIC [1] MOSAIC [2] () (n) () 2. 1: (a) (b) t x(t) y(t) (x(0), y(0)), (x(1), y(1)), · · · , (x(T), y(T)) 2.1 x(t) j select (1(a)) ASLN(Adaptive and Sequential Learning Network)[3] ASLN I I J (1(b)) x(t) x(t) j W pa j (t) = (W pa j1 (t), · · · , W pa ji (t), · · · , W pa jI (t)) x(t) W pa j (t) O me j = W pa j (t)·x(t) j θ th,j (t) (θ min,j(More)