Complex-Valued Feedforward Neural Networks Learning Without Backpropagation Conference Paper

abstract

• 2017, Springer International Publishing AG. This paper presents an efficient learning algorithm for complex-valued feedforward neural networks with application to classification problems. It simplifies complex-valued neural networks learning by using the forward-only computation rather than traditional forward and backward computations. By incorporating the forward-only computation, the complex-valued Levenberg-Marquardt algorithm becomes more efficient. Comparison results of computation cost show that the proposed forward-only complex-valued learning algorithm can be faster than the traditional implementation of the Levenberg-Marquardt algorithm.

authors

• Huang, Tingwen

published proceedings

• NEURAL INFORMATION PROCESSING (ICONIP 2017), PT IV

author list (cited authors)

• Guo, W., Huang, H. e., & Huang, T.

citation count

• 1

complete list of authors

• Guo, Wei||Huang, He||Huang, Tingwen

publication date

• January 2017

publisher

• Springer Nature  Publisher

published in

• Lecture Notes in Artificial Intelligence  Journal

keywords

• Classification
• Complex-valued Neural Networks
• Computation Cost
• Forward-only Computation
• Levenberg-marquardt Algorithm

Digital Object Identifier (DOI)

• 10.1007/978-3-319-70093-9_11

International Standard Book Number (ISBN) 13

• 978-3-319-70092-2

start page

• 100

end page

• 107

volume

• 10637

URL

• http://dx.doi.org/10.1007/978-3-319-70093-9_11