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

Structure optimization of neural networks with the A*-algorithm.

A Doering¹, M Galicki, H Witte

¹Inst. of Med. Stat., Friedrich-Schiller-Univ., Jena.

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

<i>Meloidogyne marylandi</i> is Involved in, but not the Primary Cause of Creeping Bentgrass Decline of Putting Greens in Southern California.

Journal of nematology·2024

Same author

Update: The molecular spectrum of virus-associated high-grade B-cell non-Hodgkin lymphomas.

Blood reviews·2024

Same author

Topographical principles and peculiarities of operative access in lumbar disc extrusion.

Der Orthopade·2017

Same author

Exploring the shock response of spider webs.

Journal of the mechanical behavior of biomedical materials·2015

Same author

Assignment of Empirical Mode Decomposition Components and Its Application to Biomedical Signals.

Methods of information in medicine·2015

Same author

Track C. Nano- and Physikalischchemische Systeme.

Biomedizinische Technik. Biomedical engineering·2015

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

This study introduces an A*-algorithm-based method for designing optimal feedforward neural network structures. The approach ensures solution and search optimality, outperforming cascade-correlation in tested examples.

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Designing optimal feedforward neural networks is crucial for effective machine learning.
Existing methods like cascade-correlation have limitations in guaranteeing structural optimality.

Purpose of the Study:

To introduce a novel method for constructing optimal feedforward neural network structures.
To ensure both solution and search optimality in neural network design.

Main Methods:

A graph-based representation of network structures with assigned evaluation values.
Implementation of an A*-algorithm heuristic search on the constructed graph.
Comparison of the new strategy against the cascade-correlation procedure.

Related Experiment Videos

Main Results:

The A*-algorithm guarantees theoretical optimality for both the solution and the search process.
Empirical comparisons demonstrate superior performance of the new strategy over cascade-correlation for certain network structures.

Conclusions:

The proposed A*-algorithm-based method provides a theoretically sound and practically effective approach to optimal feedforward neural network construction.
This method offers a promising alternative for designing high-performance neural network architectures.