A stochastic backpropagation algorithm for training neural networks

A stochastic backpropagation algorithm for training neural networks

The popularly used backpropagation algorithm (BP) for training multilayered neural networks is generally slow and prone to getting stuck in local minima. A novel method to improve the performance of the BP by randomising the cost function is proposed. The method is effective in helping the BP algori...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Y.Q., Yin, T., Babri, H.A.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Backpropagation algorithms
Convergence
Cost function
Entropy
Feedforward neural networks
Jacobian matrices
Multi-layer neural network
Neural networks
Pattern recognition
Stochastic processes
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The popularly used backpropagation algorithm (BP) for training multilayered neural networks is generally slow and prone to getting stuck in local minima. A novel method to improve the performance of the BP by randomising the cost function is proposed. The method is effective in helping the BP algorithm to escape from local minima and therefore improve the convergence and generalization. This is demonstrated on a non-convex pattern recognition problem.
DOI:10.1109/ICICS.1997.652068