• Medicine, Computer Science
  • Published in IEEE Trans. Neural Networks 1997
  • DOI:10.1109/72.572108

Supervised neural networks for the classification of structures

@article{Sperduti1997SupervisedNN,
  title={Supervised neural networks for the classification of structures},
  author={Alessandro Sperduti and Antonina Starita},
  journal={IEEE transactions on neural networks},
  year={1997},
  volume={8 3},
  pages={
          714-35
        }
}
Highlight Information
Standard neural networks and statistical methods are usually believed to be inadequate when dealing with complex structures because of their feature-based approach. [...] Key Method By using generalized recursive neurons, all the supervised networks developed for the classification of sequences, such as backpropagation through time networks, real-time recurrent networks, simple recurrent networks, recurrent cascade correlation networks, and neural trees can, on the whole, be generalized to structures. The…Expand Abstract

Citations

Publications citing this paper.
SHOWING 1-10 OF 230 CITATIONS, ESTIMATED 85% COVERAGE

Neural Network for Graphs: A Contextual Constructive Approach

  • Alessio Micheli
  • Computer Science, Medicine
  • IEEE Transactions on Neural Networks
  • 2009
VIEW 19 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Recursive processing of cyclic graphs

VIEW 10 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Recursive Neural Networks for Density Estimation Over Generalized Random Graphs

VIEW 18 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Graph Matching Using Hierarchical Fuzzy Graph Neural Networks

VIEW 11 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Graph Echo State Networks

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Classification of molecular structures made easy

  • Edmondo Trentin, Ernesto Di Iorio
  • Computer Science
  • 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)
  • 2008
VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Recursive neural networks learn to localize faces

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Entropy-based generation of supervised neural networks for classification of structured patterns

VIEW 9 EXCERPTS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

1997
2020

CITATION STATISTICS

  • 24 Highly Influenced Citations

  • Averaged 16 Citations per year from 2017 through 2019

  • 29% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 33 REFERENCES

Finding Structure in Time

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Dynamics and architecture for neural computation

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Neural tree networks

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

A Learning Algorithm for Continually Running Fully Recurrent Neural Networks

VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL

Encoding of graphs for neural network processing

  • A. Sperduti, A. Starita
  • Technical Report , Dipartimento di Informatica, Universit a di Pisa
  • 1996

Stability properties of labeling recursive auto-associative memory

VIEW 1 EXCERPT