Complex-Valued Neural Networks: An Introduction

Hirose, Akira

doi:10.1142/9789812791184_0001

Cited by 135 publications

(181 citation statements)

References 0 publications

Supporting

Mentioning

181

Contrasting

Order By: Relevance

“…In fact, complex-valued neural networks (CVNN) make it possible to solve some problems which cannot be solved with their real-valued counterparts. Stimulated by works in [1,2], We consider the generalized CVNN described by the equation.…”

Section: Introductionmentioning

confidence: 99%

Global Stability of Complex-Valued Genetic Regulatory Networks with Delays on Time Scales

Wang

Chen

2016

MATEC Web of Conferences

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Global Stability of Complex-Valued Genetic Regulatory Networks with Delays on Time Scales

Wang

Chen

2016

MATEC Web of Conferences

View full text Add to dashboard Cite

show abstract

“…Complex-valued neural networks have advantages for chaotic and brain-like systems, image processing and quantum devices [6]. We identify the absolute value of a complex neuron activation with its firing rate and the phase of its activation with the phase at which its spikes are emitted.…”

Section: Introductionmentioning

confidence: 99%

Image Segmentation by Complex-Valued Units

Weber

Wermter

2005

Artificial Neural Networks: Biological Inspirations – ICANN 2005

View full text Add to dashboard Cite

Abstract. Spike synchronisation and de-synchronisation are important for feature binding and separation at various levels in the visual system. We present a model of complex valued neuron activations which are synchronised using lateral couplings. The firing rates of the model neurons correspond to a complex number's absolute value and obey conventional attractor network relaxation dynamics, while the firing phases correspond to a complex number's angle and follow the dynamics of a logistic map. During relaxation, we show that features with strong couplings are grouped by firing in the same phase and are separated in phase from features that are coupled weakly or by negative weights. In an example, we apply the model to the level of a hidden representation of an image, thereby segmenting it on an abstract level. We imply that this process can facilitate unsupervised learning of objects in cluttered background.

show abstract

“…With the system, we observe reflection and scattering to obtain a complexamplitude two-dimensional image at multiple frequencies. In the resulting 3-dimensional (2-dimensional (space) × frequency) data, we extract local texture information as a set of feature vectors, and feed them to a CSOM for adaptive classification of the 3-dimensional texture (Hirose, 2006) (Hirose, 2003). By using the system, we could visualize antipersonnel plastic landmines buried shallowly underground.…”

mentioning

confidence: 99%