Abstract: In a kernel learning apparatus, a data preprocessing circuitry preprocesses and represents each data example as a collection of feature representations that need to be interpreted. An explicit feature mapping circuit designs a kernel function with an explicit feature map to embed the feature representations of data into a nonlinear feature space and to produce the explicit feature map for the designed kernel function to train a predictive model. A convex problem formulating circuitry formulates a non-convex problem for training the predictive model into a convex optimization problem based on the explicit feature map. An optimal solution solving circuitry solves the convex optimization problem to obtain a globally optimal solution for training an interpretable predictive model.

Abstract: In a kernel learning apparatus, a data preprocessing circuitry preprocesses and represents each data example as a collection of feature representations that need to be interpreted. An explicit feature mapping circuit designs a kernel function with an explicit feature map to embed the feature representations of data into a nonlinear feature space and to produce the explicit feature map for the designed kernel function to train a predictive model. A convex problem formulating circuitry formulates a non-convex problem for training the predictive model into a convex optimization problem based on the explicit feature map. An optimal solution solving circuitry solves the convex optimization problem to obtain a globally optimal solution for training an interpretable predictive model.

Abstract: In a kernel learning apparatus, a data preprocessing circuitry preprocesses and represents each data example as a collection of feature representations that need to be interpreted. An explicit feature mapping circuit designs a kernel function with an explicit feature map to embed the feature representations of data into a nonlinear feature space and to produce the explicit feature map for the designed kernel function to train a predictive model. A convex problem formulating circuitry formulates a non-convex problem for training the predictive model into a convex optimization problem based on the explicit feature map. An optimal solution solving circuitry solves the convex optimization problem to obtain a globally optimal solution for training an interpretable predictive model.

Abstract: In a kernel learning apparatus, a data preprocessing circuitry preprocesses and represents each data example as a collection of feature representations that need to be interpreted. An explicit feature mapping circuit designs a kernel function with an explicit feature map to embed the feature representations of data into a nonlinear feature space and to produce the explicit feature map for the designed kernel function to train a predictive model. A convex problem formulating circuitry formulates a non-convex problem for training the predictive model into a convex optimization problem based on the explicit feature map. An optimal solution solving circuitry solves the convex optimization problem to obtain a globally optimal solution for training an interpretable predictive model.

Abstract: A neural network learning system in which an input-output relationship is inferred. The system includes a probability density part for determining a probability density on a sum space of an input space and an output space from a set of given input and output samples by learning, the probability density on the sum space being defined to have a parameter, and an inference part for inferring a probability density function based on the probability density from the probability density part, so that an input-output relationship of the samples is inferred from the probability density function having a parameter value determined by learning, the learning of the parameter being repeated until the value of a predefined parameter differential function using a prescribed maximum likelihood method is smaller than a prescribed reference value.

Abstract: An image forming apparatus includes a housing, a mechanism, mounted in the housing, for forming images on a medium, an operation panel formed on the housing, the mechanism being driven in accordance with an operating instruction input from the operation panel by an operator, a microphone, provided in the housing, for detecting a noise generated by a driving of the mechanism, and a noise canceling unit for outputting an acoustic wave to an area adjacent to the operation panel of the housing, the acoustic wave being generated based on the noise detected by the microphone so that the acoustic wave and a noise present in the area cancel out, whereby the noise present in the area is reduced.

Abstract: A noise controller which noise-controls a movable point so that a noise generated from a noise source and transmitted to the movable point can be reduced. The noise controller filters the noise in accordance with a least mean square algorithm and generates an antinoise to be collided with the noise so that the antinoise and the noise can cancel each other out. When a filter coefficient used for the least mean square algorithm is renewed, the noise controller uses position data of the movable point. Thus, even if the movable point moves, the proper noise-control can be performed.

Abstract: An image forming apparatus reduces the level of noise escaping therefrom via an opening. The noise is generated from a motor which drives an image forming part in the image forming apparatus, from a radiator fan which radiates heat inside the apparatus to the outside via the opening, and from an exhaust fan which passes harmful air through a filter and then exhausts harmless air to the outside via the opening. The image forming apparatus generates a predetermined sound wave and collides it with the noise so that the predetermined sound wave and noise cancel each other out.

Abstract: A pattern recognition apparatus includes a pattern input unit inputting pattern data and learning data, and a neural network system including a plurality of neural networks, each of the plurality of neural networks being assigned a corresponding one of a plurality of identification classes and having only two output units of a first unit (Uo1) and a second unit (Uo2). Learning for each of the plurality of neural networks is performed by using the learning data. The image recognition apparatus also includes judgment unit judging which one of the identification classes the pattern data input from the image reading unit belongs to on the basis of output values A and B from the two output units (Uo1) and (Uo2) of all neural networks.