Universal Approximation Capability of Cascade Correlation for Structures
Neural Computation
Neural network for graphs: a contextual constructive approach
IEEE Transactions on Neural Networks
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
An overview of AI research in Italy
Artificial intelligence
A new neural network model for contextual processing of graphs
WIRN'05 Proceedings of the 16th Italian conference on Neural Nets
Neurocomputing
Hi-index | 0.00 |
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.