On the Efficient Classification of Data Structures by Neural Networks
Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence. Neural Networks. Pages 1066-1070.
Abstract
In the last few years it has been shown that recurrent neural networks are adequate for processing general data structures like trees and graphs , which opens the doors to a number of new interesting applications previously unexplored. In this paper, we analyze the efficiency of learning the membership of DOAGs (Directed Ordered Acyclic Graphs) in terms of local minima of the error surface by relying on the principle that their absence is a guarantee of efficient learning. We give sufficient conditions under which the error surface is local minima free. Specifically, we define a topological index associated with a collection of DOAGs that makes it possible to design the architecture so as to avoid lo ca l minima.
@inproceedings{ijcai1997p154,
title = {On the Efficient Classification of Data Structures by Neural Networks},
author = {Frasconi, Paolo and Gori, Marco and Sperduti, Alessandro},
booktitle = {Proceedings of the Fifteenth International Joint Conference on
Artificial Intelligence, {IJCAI-97}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Martha E. Pollack},
pages = {1066--1070},
year = {1997},
note = {Neural Networks},
url = {https://ijcai.org/proceedings/1997/154},
}
TY - CPAPER TI - On the Efficient Classification of Data Structures by Neural Networks AU - Frasconi, Paolo AU - Gori, Marco AU - Sperduti, Alessandro T2 - Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence, IJCAI-97 PB - International Joint Conferences on Artificial Intelligence PY - 1997 SP - 1066 EP - 1070 UR - https://ijcai.org/proceedings/1997/154 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
