Abstract: A pattern classification method extracts a quantity of pattern characteristics from a pattern classification target, registers/sets in a pattern dictionary classification category information corresponding to the quantity of pattern characteristics, performs pattern classification based on the quantity of pattern characteristics and a Mahalanobis dictionary registered in the pattern dictionary, and creates the Mahalanobis dictionary by effecting optimization processing of the pattern dictionary based on the classification category name and the quantity of pattern characteristics.

Abstract: A pattern classification method extracts a quantity of pattern characteristics from a pattern classification target, registers/sets in a pattern dictionary classification category information corresponding to the quantity of pattern characteristics, performs pattern classification based on the quantity of pattern characteristics and a Mahalanobis dictionary registered in the pattern dictionary, and creates the Mahalanobis dictionary by effecting optimization processing of the pattern dictionary based on the classification category name and the quantity of pattern characteristics.

Abstract: A dot-code recording method includes a step of generating a plurality of one-block dot patterns, each of which comprises a plurality of dots. The plurality of one-block dot patterns are then arranged to represent multimedia information, and a specific range of the plurality of one-block dot patterns are distributed according to specific rules to thereby arrange the one-block dot patterns within the specific range in non-time sequence. The non-time sequence distributed one-block dot patterns are then recorded on a recording medium.

Abstract: A neuron unit comprises a synapse section in which input signals from external input means or preceding neuron units and synaptic weights are multiplied, and a neuron section in which output signals of the synapse section are added, subjected to thresholding, subjected to linear or nonlinear conversion, and then outputted to the outside. According to an aspect of the present invention, a synaptic weight used in the synapse section and/or a threshold used in the neuron section, which corresponds in magnitude to an external input, is obtained through interpolation from synaptic weights which have been learned previously, varying in magnitude according to external inputs. According to the other aspect of the present invention, the synaptic weight and/or the threshold is obtained in accordance with a previously set function of an external input.

Abstract: A voice coding apparatus has a first linear prediction analyzer for acquiring linear prediction coefficients based on a received input speech sampled at a given time interval. A synthesized speech LPC code book stores linear prediction coefficients of a speech resynthesized based on an old input speech. An excitation code book has predetermined excitation vectors. A first error minimizer receives a signal representing an error between the linear prediction coefficient from the first linear prediction analyzer and one linear prediction coefficient of the synthesized speech LPC code book and acquires an index of the synthesized speech LPC code book which minimizes the error. A linear predictor computes a predictive speech based on the index, acquired by the first error minimizer, and an excitation vector of the excitation code book.

Abstract: An optimization apparatus using a layered neural network having an input layer formed of input units and supplied with input data and an output layer formed of output units connected to the individual input units with specified synaptic weights, which comprises a calculator circuit for calculating, for each output unit, the degree of similarity between the input data and the synaptic weight as well as the evaluation function value by causing the optimization problem to correspond to the fired units in the output layer, a detector for detecting the best matching optimum output unit on the basis of the output of the calculator circuit, and a self-organization circuit for changing the synaptic weights of a group of the output units associated with the optimum unit detected by the detector.

Abstract: In a focus detection device for a camera, a plurality of distance sensors each for detecting a distance to an object in a plurality of areas of a photographing image plane are provided and distance data obtained by the distance sensors for each object in each area is supplied to a main object detection circuit and a normalizing circuit. The normalizing circuit normalizes the distance data into a real number ranging from 0 to 1 and then supplies the same to a neural network. The neural network formed of a single-layered neuron units of which the synapse connection weighting factors are previously obtained by the learning process, calculates a vector difference between the distance data and the synapse connection weighting factors of each neuron unit, detects the minimum vector difference, and outputs position data of a main object corresponding to a neuron unit which gives the minimum vector difference. The position data of the main object is input to a main object detection circuit.

Abstract: In an electronic still camera apparatus wherein an image of an object is incident on an image pickup surface of a CCD through an optical lens, the object image passed the optical lens is divided into a portion entering the CCD and a portion entering a two-dimensional PSD. The two-dimensional PSD detects a center of gravity of a light distribution of the object image, and a detection signal is supplied to a deviation detector comprising a sample-hold circuit and a differential amplifier. The deviation detector stores the detection signal at the time of start of image pickup, and the differential amplifier compares the stored signal and a detection signal output from the PSD during image pickup. A deviation detection signal corresponding to the comparison result is output.