Loo Chu Kiong, Rajeswari Mandava, Rao M V C
Faculty of Engineering and Technology, Multimedia University, 75450 Melaka, Malaysia.
IEEE Trans Neural Netw. 2004 Nov;15(6):1378-95. doi: 10.1109/TNN.2004.837779.
This paper presents two novel approaches to determine optimum growing multi-experts network (GMN) structure. The first method called direct method deals with expertise domain and levels in connection with local experts. The growing neural gas (GNG) algorithm is used to cluster the local experts. The concept of error distribution is used to apportion error among the local experts. After reaching the specified size of the network, redundant experts removal algorithm is invoked to prune the size of the network based on the ranking of the experts. However, GMN is not ergonomic due to too many network control parameters. Therefore, a self-regulating GMN (SGMN) algorithm is proposed. SGMN adopts self-adaptive learning rates for gradient-descent learning rules. In addition, SGMN adopts a more rigorous clustering method called fully self-organized simplified adaptive resonance theory in a modified form. Experimental results show SGMN obtains comparative or even better performance than GMN in four benchmark examples, with reduced sensitivity to learning parameters setting. Moreover, both GMN and SGMN outperform the other neural networks and statistical models. The efficacy of SGMN is further justified in three industrial applications and a control problem. It provides consistent results besides holding out a profound potential and promise for building a novel type of nonlinear model consisting of several local linear models.
本文提出了两种新颖的方法来确定最优生长多专家网络（GMN）结构。第一种方法称为直接法，它处理与本地专家相关的专业领域和水平。生长神经气（GNG）算法用于对本地专家进行聚类。误差分布的概念用于在本地专家之间分配误差。在达到指定的网络规模后，调用冗余专家去除算法，根据专家的排名来修剪网络规模。然而，由于网络控制参数过多，GMN不符合人体工程学。因此，提出了一种自调节GMN（SGMN）算法。SGMN对梯度下降学习规则采用自适应学习率。此外，SGMN采用一种经过修改的、更为严格的聚类方法，即完全自组织简化自适应共振理论。实验结果表明，在四个基准示例中，SGMN获得了与GMN相当甚至更好的性能，对学习参数设置的敏感性降低。此外，GMN和SGMN均优于其他神经网络和统计模型。SGMN的有效性在三个工业应用和一个控制问题中得到了进一步验证。它除了为构建一种由多个局部线性模型组成的新型非线性模型展现出巨大潜力和前景外，还提供了一致的结果。
