Parallel and distributed systems for constructive neural network learning

A constructive learning algorithm dynamically creates a problem-specific neural network architecture rather than learning on a pre-specified architecture. The authors propose a parallel version of their recently presented constructive neural network learning algorithm. Parallelization provides a com...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:High-Performance Distributed Computing, 2nd International Symposium (HPDC-2 S. 174 - 186
Hauptverfasser: Fletcher, J., Obradovic, Z.
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE Comput. Soc. Press 1993
Schlagworte:
Computer architecture
Computer networks
Computer science
Feedforward neural networks
Feedforward systems
Heuristic algorithms
Network topology
Neural networks
Neurons
Workstations
ISBN:0818639008, 9780818639005
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A constructive learning algorithm dynamically creates a problem-specific neural network architecture rather than learning on a pre-specified architecture. The authors propose a parallel version of their recently presented constructive neural network learning algorithm. Parallelization provides a computational speedup by a factor of O(t) where t is the number of training examples. Distributed and parallel implementations under p4 using a network of workstations and a Touchstone DELTA are examined. Experimental results indicate that algorithm parallelization may result not only in improved computational time, but also in better prediction quality.< >
ISBN:0818639008
9780818639005
DOI:10.1109/HPDC.1993.263844