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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:High-Performance Distributed Computing, 2nd International Symposium (HPDC-2 s. 174 - 186
Hlavní autoři: Fletcher, J., Obradovic, Z.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE Comput. Soc. Press 1993
Témata:
Computer architecture
Computer networks
Computer science
Feedforward neural networks
Feedforward systems
Heuristic algorithms
Network topology
Neural networks
Neurons
Workstations
ISBN:0818639008, 9780818639005
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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