Back-propagation algorithm with variable adaptive momentum

•Back-propagation neural network (BPNN).•Variable Adaptive Momentum.•Supervised Learning Algorithms.•Deep Learning. In this paper, we propose a novel machine learning classifier by deriving a new adaptive momentum back-propagation (BP) artificial neural networks algorithm. The proposed algorithm is...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Knowledge-based systems Ročník 114; s. 79 - 87
Hlavní autoři: Hameed, Alaa Ali, Karlik, Bekir, Salman, Mohammad Shukri
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 15.12.2016
Témata:
Adaptive momentum
Back-propagation
Neural network
Supervised learning
Neural network
Supervised learning
Back-propagation
Adaptive momentum
ISSN:0950-7051, 1872-7409
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•Back-propagation neural network (BPNN).•Variable Adaptive Momentum.•Supervised Learning Algorithms.•Deep Learning. In this paper, we propose a novel machine learning classifier by deriving a new adaptive momentum back-propagation (BP) artificial neural networks algorithm. The proposed algorithm is a modified version of the BP algorithm to improve its convergence behavior in both sides, accelerate the convergence process for accessing the optimum steady-state and minimizing the error misadjustment to improve the recognized patterns superiorly. This algorithm is controlled by the learning rate parameter which is dependent on the eigenvalues of the autocorrelation matrix of the input. It provides low error performance for the weights update. To discuss the performance measures of this proposed algorithm and the other supervised learning algorithms such as k-nearest neighbours (k-NN), Naive Bayes (NB), linear discriminant analysis (LDA), support vector machines (SVM), BP, and BP with adaptive momentum (PBPAM) have been compared in term of speed of convergence, Sum of Squared Error (SSE), and accuracy by implementing benchmark problem - XOR and seven datasets from UCI repository.
ISSN:0950-7051
1872-7409
DOI:10.1016/j.knosys.2016.10.001