Micheli Alessio, Sona Diego, Sperduti Alessandro
Computer Science Department, University of Pisa, 56127 Pisa, Italy.
IEEE Trans Neural Netw. 2004 Nov;15(6):1396-410. doi: 10.1109/TNN.2004.837783.
This paper propose a first approach to deal with contextual information in structured domains by recursive neural networks. The proposed model, i.e., contextual recursive cascade correlation (CRCC), a generalization of the recursive cascade correlation (RCC) model, is able to partially remove the causality assumption by exploiting contextual information stored in frozen units. We formally characterize the properties of CRCC showing that it is able to compute contextual transductions and also some causal supersource transductions that RCC cannot compute. Experimental results on controlled sequences and on a real-world task involving chemical structures confirm the computational limitations of RCC, while assessing the efficiency and efficacy of CRCC in dealing both with pure causal and contextual prediction tasks. Moreover, results obtained for the real-world task show the superiority of the proposed approach versus RCC when exploring a task for which it is not known whether the structural causality assumption holds.
本文提出了一种通过递归神经网络处理结构化领域中上下文信息的初步方法。所提出的模型，即上下文递归级联相关（CRCC），是递归级联相关（RCC）模型的推广，它能够通过利用存储在冻结单元中的上下文信息部分消除因果关系假设。我们正式刻画了CRCC的属性，表明它能够计算上下文转导以及一些RCC无法计算的因果超源转导。在受控序列和涉及化学结构的实际任务上的实验结果证实了RCC的计算局限性，同时评估了CRCC在处理纯因果和上下文预测任务方面的效率和有效性。此外，在实际任务中获得的结果表明，当探索一个未知结构因果关系假设是否成立的任务时，所提出的方法相对于RCC具有优越性。
