Error Back Propagation Algorithm with Adaptive Learning Rate

Error Back Propagation algorithm is one of the most popular method for training artificial neural networks. Unfortunately, this is also one of the slowest due to constant and small learning rate parameter used to update weights of neurons. There are therefore many methods for dynamic change this par...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:The International Conference on Information and Digital Technologies (Online) s. 216 - 222
Hlavní autoři: Kolbusz, Janusz, Rozycki, Pawel, Lysenko, Oleksandr, Wilamowski, Bogdan M.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2019
Témata:
Adaptive learning
Approximation algorithms
Artificial neural networks
Backpropagation
EBP algorithm
Estimation
gradient descent
Heuristic algorithms
learning rate estimation
Neurons
Training
ISSN:2575-677X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Error Back Propagation algorithm is one of the most popular method for training artificial neural networks. Unfortunately, this is also one of the slowest due to constant and small learning rate parameter used to update weights of neurons. There are therefore many methods for dynamic change this parameter in the adaptive manner. In this paper has been presented new method based on estimation of learning rate with respect of approximation for the value of output error.
ISSN:2575-677X
DOI:10.1109/DT.2019.8813440