Convergence Analysis of Batch Gradient Algorithm for Three Classes of Sigma-Pi Neural Networks

Sigma-Pi (Σ-Π) neural networks (SPNNs) are known to provide more powerful mapping capability than traditional feed-forward neural networks. A unified convergence analysis for the batch gradient algorithm for SPNN learning is presented, covering three classes of SPNNs: Σ-Π-Σ, Σ-Σ-Π and Σ-Π-Σ-Π. The m...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Neural processing letters Ročník 26; číslo 3; s. 177 - 189
Hlavní autoři:	Zhang, Chao, Wu, Wei, Xiong, Yan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Dordrecht Springer 01.12.2007 Springer Nature B.V
Témata:	Algorithms Applied sciences Artificial intelligence Computer science; control theory; systems Connectionism. Neural networks Convergence Error functions Exact sciences and technology Machine learning Neural networks Sigma-Pi-Sigma-Pi neural networks, Batch gradient algorithm Gradient Error function 74P05 Monotonicity, 92B20 Neural network Sigma-Sigma-Pi neural networks Search algorithm Batch process Batch production Convergence, Sigma-Pi-Sigma neural networks Learning algorithm Artificial intelligence 68Q32 Algorithm analysis Monotonicity
ISSN:	1370-4621, 1573-773X
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Sigma-Pi (Σ-Π) neural networks (SPNNs) are known to provide more powerful mapping capability than traditional feed-forward neural networks. A unified convergence analysis for the batch gradient algorithm for SPNN learning is presented, covering three classes of SPNNs: Σ-Π-Σ, Σ-Σ-Π and Σ-Π-Σ-Π. The monotonicity of the error function in the iteration is also guaranteed.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ISSN:	1370-4621 1573-773X
DOI:	10.1007/s11063-007-9050-0