Related Concept Videos
Social Foundations of Self IV: Self in Digital Communication
Communication
Communication
One-Way ANOVA: Equal Sample Sizes
Different sample means can result in different values for the variance estimate: variance between samples. This is because the variance between samples is calculated as the product of the sample size and the variance between the...
Electric Field of Two Equal and Opposite Charges
A separation of the positive and negative charges can lead to a weak, remnant effect of the positive and negative charges. The expectation is that the more the distance between the positive and...
Dimensional Analysis
Conversion Factors and Dimensional Analysis
The unit...
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Subgroup-Specific Associations of GRIA Genes Encoding AMPA Glutamate Receptor Subunits with Patient Survival in Medulloblastoma.
Opposite patterns of association of TWIST1 expression with patient survival in SHH and Group 4 medulloblastoma.
Related Experiment Video
Updated: Feb 2, 2026

Three-dimensional Optical-resolution Photoacoustic Microscopy
Published on: May 3, 2011
Butterfly neural equalizer applied to optical communication systems with two-dimensional digital modulation.
A novel Butterfly Neural Equalizer (NE-Butterfly) effectively addresses nonlinear systems in optical communications. This Artificial Neural Network (ANN) architecture demonstrates superior performance in equalizing complex fiber optic channels.
More Related Videos
10:45Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling
Published on: May 31, 2017
06:36Optrode Array for Simultaneous Optogenetic Modulation and Electrical Neural Recording
Published on: September 1, 2022
Area of Science:
- Optical Communications
- Artificial Intelligence
- Signal Processing
Background:
- Nonlinear systems in optical communications pose significant equalization challenges.
- Existing neural equalizers struggle with complex channel characteristics.
Purpose of the Study:
- Introduce and evaluate a new equalizer architecture, the Butterfly Neural Equalizer (NE-Butterfly).
- Assess the NE-Butterfly's capability to equalize linear and nonlinear channels with real or complex taps.
Main Methods:
- Developed a novel equalizer architecture inspired by the butterfly equalizer.
- Utilized Multi-Layer Perceptron (MLP) type Artificial Neural Networks (ANNs).
- Conducted simulations on nonlinear fiber optic channels with inter-symbol interference and additive noise.
Main Results:
- The NE-Butterfly successfully equalized diverse nonlinear fiber optic channels.
- Demonstrated robust performance against channels with complex and real taps.
- Achieved superior performance compared to existing neural equalizers in the literature.
Conclusions:
- The NE-Butterfly offers a highly effective solution for nonlinear channel equalization in optical systems.
- This architecture presents a significant advancement in neural equalization techniques.
- The NE-Butterfly validates its superior performance through comparative analysis.