Convergence of a Batch Gradient Algorithm with Adaptive Momentum for Neural Networks

In this paper, a batch gradient algorithm with adaptive momentum is considered and a convergence theorem is presented when it is used for two-layer feedforward neural networks training. Simple but necessary sufficient conditions are offered to guarantee both weak and strong convergence. Compared wit...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Neural processing letters Ročník 34; číslo 3; s. 221 - 228
Hlavní autoři: Shao, Hongmei, Xu, Dongpo, Zheng, Gaofeng
Médium: Journal Article
Jazyk:angličtina
Vydáno: Boston Springer US 01.12.2011
Springer
Springer Nature B.V
Témata:
Adaptive algorithms
Applied sciences
Artificial Intelligence
Artificial neural networks
Complex Systems
Computational Intelligence
Computer Science
Computer science; control theory; systems
Connectionism. Neural networks
Convergence
Error functions
Exact sciences and technology
Momentum
Neural network
Gradient algorithm
Adaptive momentum
Convergence
Gradient
Adaptive algorithm
Error function
Adaptive method
Search algorithm
Batch process
Batch production
Feedforward
Quadratic function
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:In this paper, a batch gradient algorithm with adaptive momentum is considered and a convergence theorem is presented when it is used for two-layer feedforward neural networks training. Simple but necessary sufficient conditions are offered to guarantee both weak and strong convergence. Compared with existing general requirements, we do not restrict the error function to be quadratic or uniformly convex. A numerical example is supplied to illustrate the performance of the algorithm and support our theoretical finding.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1370-4621
1573-773X
DOI:10.1007/s11063-011-9193-x