Yoshihiro Kojima

Neural networks designed on approximate reasoning architecture and their applications

The NARA (neural networks based on approximate reasoning architecture) model is proposed and its composition procedure and evaluation are described. NARA is a neural network (NN) based on the structure of fuzzy inference rules. The distinctive feature of NARA is that its internal state can be analyzed according to the rule structure, and the problematic portion can be easily located and improved. The ease with which performance can be improved is shown by applying the NARA model to pattern classification problems. The NARA model is shown to be more efficient than ordinary NN models. In NARA, characteristics of the application task can be built into the NN model in advance by employing the logic structure, in the form of fuzzy inference rules. Therefore, it is easier to improve the performance of NARA, in which the internal state can be observed because of its structure, than that of an ordinary NN model, which is like a black box. Examples are introduced by applying the NARA model to the problems of auto adjustment of VTR tape running mechanisms and alphanumeric character recognition.

Recognition of handwritten numeric characters using neural networks designed on approximate reasoning architecture

We have newly developed a handwritten numeric character recognition system with neural networks based on an approximate reasoning architecture (NARA). Handwritten character recognition is one of the most difficult tasks in an area of pattern recognition because of the variation of handwritten images even in a same category of character. NARA, which consists of a classifier of input data, several sub-neural networks and an integrator of the outputs of sub-neural networks can realize a stable recognition of large variations of handwritten character images, and achieved a correct answer rate of 95.41%, an error rate of 0.20% and a rejection rate of 4.38%.

Adaptive segmentation of quantizer neuron architecture (ASQA)

The authors have previously proposed a multi functional layered network (MFLN) employing a quantizer neuron model and proved that a learning speed of MFLN is the fastest among RCE networks, LVQ3 and multi-layered neural network with backpropagation. The authors also proved that MFLN has very nice supplemental learning performance and can realize adaptive learning or filtering. One of the biggest issues of neural networks is how to design the network structure. In this paper the authors propose an adaptive segmentation of quantizer neuron architecture (ASQA) for answering the above issue and apply them to handwritten character recognition. The networks based on ASQA consist of quantizer neurons which can proliferate themselves and form the optimum network structure for the recognition automatically during training. As a result, there is no need to design the structure of the networks and the average accuracy of the closed and the open test of 27,200 handwritten numeric characters increased to 99.6%. The best tuning of a segmentation threshold of quantizer neurons produced the optimum network size of ASQA.

Character recognition system with cooperation of pattern and symbolic processing

A newly developed character recognition method is proposed that can be applied to low quality printed documents. In this method, the cooperation of pattern processing with neural networks and symbolic processing with knowledge of language is adopted. If errors occur at one part, another part detects it and sends the error information to all parts. After successive iterations until no error is detected, a recognition result is obtained. A character recognition of 98.4 percent is obtained with this method. This rate is 2.8 percent higher than the result of a conventional method with no information exchange among processing parts.

Multifunctional layered network with quantizer neurons

The authors propose a multifunctional layered network (MFLN) with a quantizer neuron model and describe the principles of the quantizer neuron and the structure of the network for a character recognition system. Each layer of the MFLN has a specific function defined by the quantizer input of the quantizer neuron, and its learning speed is extremely fast. The authors have applied it to a character recognition system and tested its initial and supplemental learning performance in comparison with three other network models (RCE networks, LVQ3, and a multilayered neural network with back-propagation). For initial learning of ten fonts, the MFLN is fastest, and it is 40 times faster than the multilayered neural network with back-propagation. For supplemental learning with seven further fonts also, the MFLN is the fastest, and it is 600 times faster than the multilayered neural network with back-propagation. The recognition rate for 10 of the fonts learned initially is 97.4% after the MFLN has learned supplementary fonts, and the MFLN displays the lowest degradation of the recognition rate of initially learned fonts.<<ETX>>