Takagi H, Suzuki N, Koda T, Kojima Y
Matsushita Electric Ind. Co. Ltd., Osaka.
IEEE Trans Neural Netw. 1992;3(5):752-60. doi: 10.1109/72.159063.
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.
提出了NARA（基于近似推理架构的神经网络）模型，并描述了其构建过程和评估方法。NARA是一种基于模糊推理规则结构的神经网络（NN）。NARA的独特之处在于，可以根据规则结构分析其内部状态，并且可以轻松定位和改进有问题的部分。通过将NARA模型应用于模式分类问题，展示了其性能提升的容易程度。结果表明，NARA模型比普通的NN模型更高效。在NARA中，可以通过采用模糊推理规则形式的逻辑结构，预先将应用任务的特征构建到NN模型中。因此，与普通的类似黑箱的NN模型相比，由于NARA的结构可以观察其内部状态，所以更容易提高其性能。通过将NARA模型应用于VTR磁带运行机制的自动调整和字母数字字符识别问题，引入了相关示例。
