Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Supervised neural networks for the classification of structures.

A Sperduti¹, A Starita

¹Dipartimento di Inf., Pisa Univ.

IEEE Transactions on Neural Networks

|January 1, 1997

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Multi-task learning for the prediction of wind power ramp events with deep neural networks.

Neural networks : the official journal of the International Neural Network Society·2020

Same author

The neutron camera upgrade for MAST Upgrade.

The Review of scientific instruments·2018

Same author

Compositional generative mapping for tree-structured data--part II: topographic projection model.

IEEE transactions on neural networks and learning systems·2014

Same author

A general framework for adaptive processing of data structures.

IEEE transactions on neural networks·2008

Same author

On the implementation of frontier-to-root tree automata in recursive neural networks.

IEEE transactions on neural networks·2008

Same author

A self-organizing map for adaptive processing of structured data.

IEEE transactions on neural networks·2008

Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013

Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011

Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011

Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011

Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011

Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011

See all related articles

Neural networks can classify complex structures using generalized recursive neurons, overcoming limitations of traditional feature-based methods. This approach enhances pattern recognition for structured data.

Area of Science:

Artificial Intelligence
Machine Learning
Computational Neuroscience

Background:

Traditional neural networks and statistical methods struggle with complex structures due to their reliance on feature-based approaches.
Feature-based methods are sensitive to a priori feature selection and cannot adequately represent relationships within structures.
This limitation hinders satisfactory solutions for structured data classification.

Purpose of the Study:

To demonstrate that neural networks can effectively represent and classify structured patterns.
To introduce and utilize the "generalized recursive neuron" as a novel approach for handling structures.
To adapt existing sequence-classification neural networks for structural data.

Main Methods:

The core innovation is the "generalized recursive neuron," an extension of recurrent neurons to handle structures.

Related Experiment Videos

Supervised networks for sequence classification, including backpropagation through time (BPTT), real-time recurrent networks (RTRN), simple recurrent networks (SRN), recurrent cascade correlation networks (RCCN), and neural trees, were generalized.

These generalized networks were applied to the classification of structured patterns, specifically logic terms.

Main Results:

The study presents results demonstrating the successful application of generalized recursive neuron networks to structured pattern classification.
Networks adapted with generalized recursive neurons showed capability in classifying logic terms.
The approach overcomes the inherent limitations of traditional feature-based methods for structured data.

Conclusions:

Neural networks, when augmented with generalized recursive neurons, are capable of representing and classifying complex structured patterns.
This generalized approach extends the applicability of established sequence-processing neural network architectures to structural data.
The findings suggest a powerful new direction for machine learning in handling hierarchical and relational data.