Gou Zhenkun, Fyfe Colin
Applied Computational Intelligence Research Unit, The University of Paisley, Paisley, Scotland PA1 2BE, UK.
Neural Netw. 2004 Mar;17(2):285-93. doi: 10.1016/j.neunet.2003.07.002.
We review a recent neural implementation of Canonical Correlation Analysis and show, using ideas suggested by Ridge Regression, how to make the algorithm robust. The network is shown to operate on data sets which exhibit multicollinearity. We develop a second model which not only performs as well on multicollinear data but also on general data sets. This model allows us to vary a single parameter so that the network is capable of performing Partial Least Squares regression (at one extreme) to Canonical Correlation Analysis (at the other)and every intermediate operation between the two. On multicollinear data, the parameter setting is shown to be important but on more general data no particular parameter setting is required. Finally, we develop a second penalty term which acts on such data as a smoother in that the resulting weight vectors are much smoother and more interpretable than the weights without the robustification term. We illustrate our algorithms on both artificial and real data.
我们回顾了一种最近的典型相关分析的神经实现方式，并利用岭回归提出的思路展示了如何使该算法具有鲁棒性。结果表明，该网络可在呈现多重共线性的数据集上运行。我们开发了第二个模型，它不仅在多重共线性数据上表现良好，而且在一般数据集上也表现出色。这个模型允许我们改变单个参数，使得网络能够执行偏最小二乘回归（在一个极端情况下）到典型相关分析（在另一个极端情况下）以及两者之间的每一个中间操作。在多重共线性数据上，参数设置被证明是重要的，但在更一般的数据上则不需要特定的参数设置。最后，我们开发了第二个惩罚项，它作用于此类数据时起到平滑器的作用，因为与没有鲁棒化项的权重相比，得到的权重向量更加平滑且更易于解释。我们在人工数据和真实数据上都展示了我们的算法。
