Abstract: A method for determining whether a fuzzy symbol matches a predetermined reference pattern by generating membership functions that collectively represent a reference pattern having identifying features; sampling the fuzzy symbol to generate an input pattern representative of the fuzzy symbol; transforming the input pattern to generate an inverted input pattern; comparing the input pattern with a first membership function to determine a first quantity of identifying features of the reference pattern that are present in the fuzzy symbol; comparing the inverted input pattern with a second membership function to determine a second quantity of identifying features of the reference pattern that are present in the fuzzy symbol; and determining that the fuzzy symbol matches the reference pattern if the first and second quantities are sufficiently high.

Abstract: In a defuzzification system having fuzzy singletons in the consequent, an inference block (1) in each rule includes a device (2) for calculating the maximum value of each fuzzy singleton, devices (3 and 4) for performing weighted and simple additions to each of the inference grades outputted from the maximum value calculating device, a device (5) (11) for dividing the weighted addition value by the simple addition value to provide a centroid value and devices (6 and 7) (12 and 13) for expanding and contracting and/or shifting the output range width of the quotient from the dividing device. Even if the input range width of the subsequent circuits and devices varies, the output range width of the centroid value can be scaled by a scaling device and also shifted by a level shifting device. The same arrangement can change and regulate the scaling or controlled variable of the consequent depending on the purpose of control.

Abstract: A fuzzy inference unit to which an input value is applied as a voltage value is provided with a scaling circuit for increasing or decreasing a range of the input value and a shifting circuit for shifting a level of the input value. The fuzzy inference unit generates a defined output as a voltage value. In the input part, an output from a preceding stage of fuzzy inference hardware can be converted into a proper value as an input value to the fuzzy inference unit. In the output part, an output of the fuzzy inference hardware can be converted into a proper value as an input to a following stage. Thus, control suited to specific purposes can be performed.

Abstract: A fuzzy inference apparatus wherein basic operation blocks used in each step of the fuzzy inference process are respectively constituted as an independent operation block and are detachable. It is preferable that a plurality of operation blocks with different basic operation systems are prepared for all or some steps of the fuzzy inference process and inputs/outputs of different basic operation blocks in the same step are compatible.

Abstract: A defuzzifying apparatus, for a fuzzy inference machine in which the consequent of a fuzzy inference is represented by a fuzzy set or a singleton, comprises a bias impression unit that adds an arbitrary-largeness bias value to each inference output grade, and circuitry a center of gravity of each inference output grade after the bias value is added. If the fuzzy inference is accomplished by hardware, it is possible to improve fluctuation of a final output due to noise or inference grade error. Even when an input does not match with any rule, any abnormal output can be prevented.

Abstract: A pattern recognition method capable of implementing a system suitable for the recognition of a complicated pattern. A reference pattern to be collated with an input pattern is represented using a plurality of membership functions to thereby apply fuzziness to the reference pattern. The input pattern which is input along a cross-detecting line is logically inverted for the production of an inverted input pattern. The input pattern is collated with any one of the plurality of membership functions to judge whether or not the input pattern is provided with at least one of the features of the reference pattern. Also, the inverted input pattern is collated with any one of the other membership functions to thereby judge whether or not the input pattern is provided with at least another one of the features of the reference pattern. The results of these inversions are synthesized.

Abstract: A fuzzy neuron device which applies the fuzzy theory and the neuron theory. The device comprises a plurality of synapses each having a membership function, a first minimum value computing circuit for extracting the minimum value signal in the device from the outputs of the plurality of synapses, an extension circuit which is a component of a second minimum value computing circuits, and an extension terminal for connecting a plurality of extension circuit to each other so as to produce the second computing circuit. A device assembly may be produced by connecting a plurality of the devices to each other. In the device assembly, the second computing circuit extracts the minimum value signal in the assembly from the plurality of minimum signals in the respective devices.

Abstract: A fuzzy inference unit includes membership function generation circuits, each of an analog type operable in an electric voltage mode. The fuzzy inference device includes thereon a sweep signal generation circuit, switches for switching the input to the membership function generating circuits between the output of the sweep signal generation circuit and an external input, and membership function observing terminals for taking out externally the outputs of the membership function generation circuits. Due to the fact that the sweep signal generation circuit is provided on the fuzzy inference unit, even if a function generator is not prepared externally, the shape of the membership function can be observed.

Abstract: A membership function generator including a maximum value arithmetic circuit for selecting a maximum voltage of a plurality of first input voltages to output the selected maximum voltage and a minimum value arithmetic circuit for selecting a minimum voltage of a plurality of second input voltages to output the selected minimum voltage. The outputs of the maximum and minimum value arithmetic circuits are input to a differential amplifier circuit. The output of the differential amplifier circuit is used as a membership function. Either at least one of the first input voltage or one of the second input voltages forms the basis of an inference and the remaining input voltages are set to a predetermined reference voltage.

Abstract: A Cardinal number extending circuit for varying a resolution of input signals within a fuzzy neuron includes a plurality of computing blocks, each of the computing blocks having a different one of a plurality of resolution levels with each of the resolution levels represented by a Cardinal number. The Cardinal number for an n-th one of said computing blocks is 2.sup.n-1 k, where k is a number corresponding to a base resolution level. A switch responsive to an external selection signal selects a computing block corresponding to one of the Cardinal numbers to generate a computed result having one of the resolution levels.

Abstract: A membership function observation device capable of reducing the number of observation terminals and reducing the time required for measurement and control so that the interrelationship among membership functions can be understood. Pairs of membership functions output from the adjacent twos of a plurality of membership function generator circuits are supplied to respective minimum value circuits to obtain respective minimum values. These minimum values are supplied to a first maximum value circuit to obtain a maximum value. In turn, all the membership functions are supplied to a second maximum value circuit to obtain the maximum value of the membership functions. The outputs of the first and second maximum value circuits are synthesized to observe all the original membership functions at the same time.

Abstract: A fuzzy inference system includes a combination of fuzzy inference units. Each of the fuzzy inference units includes a plurality of fuzzy inference circuit sections and difuzzifier and is adapted to treat an input variable to form a controlled variable in accordance with a given fuzzy control rule. In order to extend the number of input variables and/or rules, the fuzzy inference circuit section of each of the fuzzy inference units includes an external extension input terminal, an external extension output terminal, a rule extending terminal and a change-over switch. When the external extension input terminal of one fuzzy inference unit is connected to that of the other fuzzy inference unit, the number of input variables can be extended. When the rule extending terminal of one fuzzy inference unit is connected to that of the other fuzzy inference unit, the number of rules can be easily extended.

Abstract: A membership function generator comprising an adder circuit which receives input VIN and center position voltage Vx for generating one side of a membership function (MF), an inversion circuit which generates the other side of the MF, adder circuits which generate the upper base of a trapezoid MF, and an adder circuit which combines one side-and the other side of MF and also sets the MF height.