{"type":"ScholarlyArticle","title":"On the Efficient Classification of Data Structures by Neural Networks","authors":[{"name":"Paolo Frasconi","slug":"paolo-frasconi","given":"Paolo","family":"Frasconi","affiliation":""},{"name":"Marco Gori","slug":"marco-gori","given":"Marco","family":"Gori","affiliation":""},{"name":"Alessandro Sperduti","slug":"alessandro-sperduti","given":"Alessandro","family":"Sperduti","affiliation":""}],"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.","doi":null,"url":"https://ijcai.org/proceedings/1997/154","pdf":"https://ijcai.org/proceedings/1997/0154.pdf","markdown":"https://ijcai.org/proceedings/1997/154.md","bibtex":"https://ijcai.org/proceedings/1997/bibtex/154","volume":{"slug":"1997","title":"Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1997","url":"https://ijcai.org/proceedings/1997/","year":1997,"location":"Nagoya, Japan","dates":"","editors":"Martha E. Pollack","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Neural Networks","track":"Neural Networks","number":154,"pages":{"first":1066,"last":1070},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}