Abstract: A fuzzy rough classification section 7 classifies an input pattern into a plurality of category groups and calculates their attribution factors. A plurality of fine classification sections 8 calculate similarities in respective category groups. In each fine classification section 8, a weight change amount control section 82 controls the weight change amount in an associated similarity calculating section 81 in accordance with the group attribution factor selected by a second group selecting section (10), thereby enabling a cooperative learning operation among plural fine classification sections 8. A force learning control section 17 performs a supplemental learning operation, if the input pattern is rejected regardless of its correctness, until its reject judge value is reduced below a predetermined reject threshold.

Abstract: A recognition apparatus is provided with a plurality of recognition units organized in a multilayered hierarchical structure. Each of the recognition units includes a signal input section, a quantizer for performing a quantization according to a signal inputted from the signal input section, and a path selecting section for performing a selection of paths according to an output from the quantizer. The path selecting section includes a path input section having at least one path input terminal, a path output section having at least one path output terminal, a load distribution selecting section for selecting a load distribution, and a load setting section for changing the strength of connection between the path input terminal and the path output terminal according to the output of the quantizer by the use of the load distribution selected by the load distribution selecting section.

Abstract: A recognizing and judging apparatus for a learning and recognizing processing to be effectively performed in a short period of time, the apparatus including a plurality of recognition units in a multi-layered hierarchical network structure with one or more path output terminals of the recognition units of an upper layer being connected with one or more path input terminals of the recognition units of a lower layer.

Abstract: A learning machine with multi-input single-output circuits connected in hierachical structure, wherein product-sums of the output signals of input and output signal registers and the weights are obtained by the parallel processing of a plurality of product-sum computing units with a plurality of input and output signal registers being connected in cascades, thereby to render to scale down the circuit of the learning machine with the sigmoid function computing unit being one in number.

Abstract: A recognizing and judging apparatus has a network organized in a multilayered hierarchical manner and a plurality of branched tree structures corresponding to the number of inputted data. The branched tree structures are organized by a plurality of recognition units, each of which includes a signal input section and a quantizer for performing a quantization according to a signal inputted from the signal input section. Each of the recognition units further includes a path input section having at least one path input terminal, a path output section having at least one path output terminal, and a path selecting section operatively coupled with both the path input section and the path output section for performing a selection of paths according to an output of the quantizer.

Abstract: An iterative learning machine uses, as a direction of changing iterative weight, a conjugate gradient direction in place of the conventional steepest descent direction, thereby saving time. Learning rates are set dynamically. Error calculation for plural learning rates, with respect to a certain weight changing direction, are accomplished by storing a product-sum of the input signals and weights in a hidden layer and a product-sum of the input signals and the weight changing direction in the hidden layer. When the learning falls into a non-effective state where further iteration does not effectively reduce an error, the weights are adjusted in order to restart the learning.

Abstract: An improved iterative learning machine having a plurality of multi-input/single-output signal processing units connected in a hierarchical structure includes a weight coefficient change control unit which controls weight change quantities for those multi-input/single-output signal processing units having iteratively reduced errors thereby increasing the learning speed, contrary to conventional learning machines which perform a learning operation in order to minimize a square error of multi-input/single-output signal processing units in the highest hierarchy of the hierarchical structure.