Title :
Bi-causal recurrent cascade correlation
Author :
Micheli, A. ; Sona, D. ; Sperduti, A.
Author_Institution :
Dipt. di Inf., Pisa Univ., Italy
Abstract :
Recurrent neural networks fail to deal with prediction tasks which do not satisfy the causality assumption. We propose to exploit bi-causality to extend the recurrent cascade correlation model in order to deal with contextual prediction tasks. Preliminary results on artificial data show the ability of the model to preserve the prediction capability of recurrent cascade correlation on strict causal tasks, while extending this capability also to prediction tasks involving the future
Keywords :
causality; directed graphs; prediction theory; recurrent neural nets; bi-causal recurrent cascade correlation; bi-causality; contextual prediction tasks; prediction capability; strict causal tasks; Context modeling; Delay effects; Electronic mail; Equations; Feedforward systems; Predictive models; Proteins; Recurrent neural networks; Training data;
Conference_Titel :
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location :
Como
Print_ISBN :
0-7695-0619-4
DOI :
10.1109/IJCNN.2000.861272
