Generalized backpropagation algorithm for training second‐order neural networks

The artificial neural network is a popular framework in machine learning. To empower individual neurons, we recently suggested that the current type of neurons could be upgraded to second‐order counterparts, in which the linear operation between inputs to a neuron and the associated weights is repla...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:International journal for numerical methods in biomedical engineering Ročník 34; číslo 5; s. e2956 - n/a
Hlavní autori: Fan, Fenglei, Cong, Wenxiang, Wang, Ge
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: England Wiley Subscription Services, Inc 01.05.2018
Predmet:
Algorithms
artificial neural network
Artificial neural networks
Back propagation
backpropagation (BP)
Fuzzy Logic
Learning algorithms
Machine Learning
Mathematical models
Neural networks
Neural Networks (Computer)
Neurons
second‐order neurons
artificial neural network
second-order neurons
backpropagation (BP)
ISSN:2040-7939, 2040-7947, 2040-7947
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The artificial neural network is a popular framework in machine learning. To empower individual neurons, we recently suggested that the current type of neurons could be upgraded to second‐order counterparts, in which the linear operation between inputs to a neuron and the associated weights is replaced with a nonlinear quadratic operation. A single second‐order neurons already have a strong nonlinear modeling ability, such as implementing basic fuzzy logic operations. In this paper, we develop a general backpropagation algorithm to train the network consisting of second‐order neurons. The numerical studies are performed to verify the generalized backpropagation algorithm. The main contribution of this paper is to propose deep neural networks consisting of quadratic artificial neurons and an associated generalized backpropagation algorithm and illustrate such networks with a number of examples. Interestingly, each quadratic neuron can be interpreted as a fuzzy logic gate, and a neural network of quadratic neurons can be naturally interpreted as a deep fuzzy logic system. Hence, we suggest to understand and develop quadratic neural networks in light of fuzzy logic theory and techniques for applications in which fuzzy logic is relevant.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2040-7939
2040-7947
2040-7947
DOI:10.1002/cnm.2956