FUZZY ARTMAP - A NEURAL NETWORK ARCHITECTURE FOR INCREMENTAL SUPERVISED LEARNING OF ANALOG MULTIDIMENSIONAL MAPS
FUZZY ARTMAP - A NEURAL NETWORK ARCHITECTURE FOR INCREMENTAL SUPERVISED LEARNING OF ANALOG MULTIDIMENSIONAL MAPS
复制标题
DOI：
10.1109/72.159059
复制
发表时间：
1992-09-01
影响因子：
--
通讯作者：
ROSEN, DB
中科院分区：
文献类型：
--
作者：
CARPENTER, GA;GROSSBERG, S;ROSEN, DB
提出了一种新的神经网络结构，用于识别类别和多维映射的增量式监督学习，以响应模拟或二进制输入向量的任意序列，这些输入向量可能代表模糊或清晰的特征集。这种被称为模糊ARTMAP的体系结构，通过利用模糊隶属关系的计算与ART类别选择、共振和学习之间的密切形式相似性，实现了模糊逻辑和自适应共振理论(ART)神经网络的综合。模糊ARTMAP还实现了一种新的极小极大学习规则，该规则联合最小化预测误差和最大化代码压缩或泛化。这是通过匹配跟踪过程来实现的，该匹配跟踪过程将ART警戒参数增加了校正预测误差所需的最小量。结果，系统自动学习最少数量的识别类别，或“隐藏单元”，以满足准确性标准。通过在预处理阶段对输入向量进行归一化来防止类别扩散。一种称为补码的标准化过程导致了一种对称理论，其中模糊逻辑的AND运算符(OR)和OR运算符(AND)扮演着互补的角色。补码编码使用ON CELL和OFF CELL来表示输入模式，并在归一化ON CELL/OFF CELL总向量的同时保留单个特征幅度。学习是稳定的，因为所有自适应权重只能随着时间的推移而减少。权重的减少与类别“框”的大小增加相对应。警戒值越小，类别框越大。通过使用输入集合的不同排序多次训练系统来实现改进的预测。这种投票策略还可以用于在给定小的、有噪声的或不完整的训练集的情况下为相互竞争的预测分配置信度估计。四类仿真展示了基准反向传播和遗传算法系统的模糊ARTMAP性能。这些模拟包括(I)寻找圆内与圆外的点；(Ii)学习区分两条螺旋；(Iii)分段连续函数的增量逼近；以及(Iv)字母识别数据库。并将模糊ARTMAP系统与Salzberg的NGE系统和Simpson的fMMC系统进行了比较。
A new 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. Fuzzy ARTMAP also realizes a new minimax learning rule that conjointly minimizes predictive error and maximizes code compression, or generalization. This is achieved by a match tracking process that increases the ART vigilance parameter by the minimum amount needed to correct a predictive error. As a result, the system automatically learns a minimal number of recognition categories, or "hidden units," to meet accuracy criteria. Category proliferation is prevented by normalizing input vectors at a preprocessing stage. A normalization procedure called complement coding leads to a symmetric theory in which the AND Operator (OR) and the OR operator (AND) of fuzzy logic play complementary roles. Complement coding uses on cells and off cells to represent the input pattern, and preserves individual feature amplitudes while normalizing the total on cell/off cell vector. Learning is stable because all adaptive weights can only decrease in time. Decreasing weights correspond to increasing sizes of category "boxes." Smaller vigilance values lead to larger category boxes. Improved prediction is achieved by training the system several times using different orderings of the input set. This voting strategy can also be used to assign confidence estimates to competing predictions given small, noisy, or incomplete training sets. Four classes of simulations illustrate fuzzy ARTMAP performance in relation to benchmark back-propagation and genetic algorithm systems. These simulations include (i) finding points inside versus outside a circle; (ii) learning to tell two spirals apart, (iii) incremental approximation of a piecewise-continuous function; and (iv) a letter recognition database. The fuzzy ARTMAP system is also compared with Salzberg's NGE system and with Simpson's FMMC system.