Sperduti A, Starita A
Dipartimento di Inf., Pisa Univ.
IEEE Trans Neural Netw. 1997;8(3):714-35. doi: 10.1109/72.572108.
Standard neural networks and statistical methods are usually believed to be inadequate when dealing with complex structures because of their feature-based approach. In fact, feature-based approaches usually fail to give satisfactory solutions because of the sensitivity of the approach to the a priori selection of the features, and the incapacity to represent any specific information on the relationships among the components of the structures. However, we show that neural networks can, in fact, represent and classify structured patterns. The key idea underpinning our approach is the use of the so called "generalized recursive neuron", which is essentially a generalization to structures of a recurrent neuron. By using generalized recursive neurons, all the supervised networks developed for the classification of sequences, such as backpropagation through time networks, real-time recurrent networks, simple recurrent networks, recurrent cascade correlation networks, and neural trees can, on the whole, be generalized to structures. The results obtained by some of the above networks (with generalized recursive neurons) on the classification of logic terms are presented.
标准神经网络和统计方法由于其基于特征的方法，通常被认为在处理复杂结构时是不够的。事实上，基于特征的方法通常无法给出令人满意的解决方案，因为该方法对特征的先验选择敏感，并且无法表示关于结构组件之间关系的任何特定信息。然而，我们表明神经网络实际上可以表示和分类结构化模式。支撑我们方法的关键思想是使用所谓的“广义递归神经元”，它本质上是对递归神经元结构的一种推广。通过使用广义递归神经元，为序列分类开发的所有监督网络，如时间反向传播网络、实时递归网络、简单递归网络、递归级联相关网络和神经树，总体上都可以推广到结构。给出了上述一些网络（带有广义递归神经元）在逻辑项分类上获得的结果。
