Carpenter G A, Grossberg S, Markuzon N, Reynolds J H, Rosen D B
Center for Adaptive Syst., Boston Univ., MA.
IEEE Trans Neural Netw. 1992;3(5):698-713. doi: 10.1109/72.159059.
A neural network architecture is introduced for incremental supervised learning of recognition categories and multidimensional maps in response to arbitrary sequences of analog or binary input vectors, which may represent fuzzy or crisp sets of features. The architecture, called fuzzy ARTMAP, achieves a synthesis of fuzzy logic and adaptive resonance theory (ART) neural networks by exploiting a close formal similarity between the computations of fuzzy subsethood and ART category choice, resonance, and learning. Four classes of simulation illustrated fuzzy ARTMAP performance in relation to benchmark backpropagation and generic algorithm systems. These simulations include finding points inside versus outside a circle, learning to tell two spirals apart, incremental approximation of a piecewise-continuous function, and a letter recognition database. The fuzzy ARTMAP system is also compared with Salzberg's NGE systems and with Simpson's FMMC system.
本文介绍了一种神经网络架构，用于对识别类别和多维映射进行增量监督学习，以响应模拟或二进制输入向量的任意序列，这些向量可能代表模糊或清晰的特征集。该架构称为模糊ARTMAP，通过利用模糊子集隶属度计算与ART类别选择、共振和学习之间的紧密形式相似性，实现了模糊逻辑与自适应共振理论（ART）神经网络的综合。四类仿真展示了模糊ARTMAP相对于基准反向传播和遗传算法系统的性能。这些仿真包括在圆内和圆外找点、学习区分两个螺旋、分段连续函数的增量逼近以及一个字母识别数据库。还将模糊ARTMAP系统与萨尔茨伯格的NGE系统和辛普森的FMMC系统进行了比较。
