Complex-Valued multilayer perceptron search utilizing eigen vector descent and reducibility mapping

Authors:
Shinya Suzumura;Ryohei Nakano
Affiliations:
Chubu University, Kasugai, Japan;Chubu University, Kasugai, Japan
Venue:
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part II
Year:
2012

Citing 6
Cited 0

Original Contribution: Uniqueness of the weights for minimal feedforward nets with a given input-output map

Neural Networks
Local minima and plateaus in hierarchical structures of multilayer perceptions

Neural Networks
Approximation by fully complex multilayer perceptrons

Neural Computation
On activation functions for complex-valued neural networks: existence of energy functions

ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
Wirtinger calculus based gradient descent and levenberg-marquardt learning algorithms in complex-valued neural networks

ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part I
The complex backpropagation algorithm

IEEE Transactions on Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A complex-valued multilayer perceptron (MLP) can approximate a periodic or unbounded function, which cannot be easily realized by a real-valued MLP. Its search space is full of crevasse-like forms having huge condition numbers; thus, it is very hard for existing methods to perform efficient search in such a space. The space also includes the structure of reducibility mapping. The paper proposes a new search method for a complex-valued MLP, which employs both eigen vector descent and reducibility mapping, aiming to stably find excellent solutions in such a space. Our experiments showed the proposed method worked well.