Contextual processing of structured data by recursive cascade correlation

Authors:
A. Micheli;D. Sona;A. Sperduti
Affiliations:
Comput. Sci. Dept., Univ. of Pisa, Italy;-;-
Venue:
IEEE Transactions on Neural Networks
Year:
2004

Citing 0
Cited 10

Universal Approximation Capability of Cascade Correlation for Structures

Neural Computation
Comparison of relevance learning vector quantization with other metric adaptive classification methods

Neural Networks
Fuzzy lattice reasoning (FLR) type neural computation for weighted graph partitioning

Neurocomputing
Neural network for graphs: a contextual constructive approach

IEEE Transactions on Neural Networks
Understanding the Principles of Recursive Neural Networks: A Generative Approach to Tackle Model Complexity

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
A preliminary empirical comparison of recursive neural networks and tree kernel methods on regression tasks for tree structured domains

Neurocomputing
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
Tree Echo State Networks

Neurocomputing
Solving graph data issues using a layered architecture approach with applications to web spam detection

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.