Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Linear Approximation in Frequency Domain01:26

Linear Approximation in Frequency Domain

144
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
144
Reconstruction of Signal using Interpolation01:10

Reconstruction of Signal using Interpolation

376
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
376
Downsampling01:20

Downsampling

274
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
274
Reducing Line Loss01:18

Reducing Line Loss

208
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
208
Linear Approximation in Time Domain01:21

Linear Approximation in Time Domain

132
Nonlinear systems often require sophisticated approaches for accurate modeling and analysis, with state-space representation being particularly effective. This method is especially useful for systems where variables and parameters vary with time or operating conditions, such as in a simple pendulum or a translational mechanical system with nonlinear springs.
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
132
Neural Regulation01:37

Neural Regulation

40.4K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
40.4K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Laser systems with a semiconductor optical amplifier and optical-power-to-electrical-current feedback.

Optics letters·2025
Same author

Impact of filtering in optical coherent systems with finite-length equalizers: modeling and experimental verification.

Optics express·2025
Same author

Bismuth-doped fiber amplifier for full S-band amplification.

Optics letters·2025
Same author

Optical neuromorphic computing via temporal up-sampling and trainable encoding on a telecom device platform.

Nanophotonics (Berlin, Germany)·2025
Same author

Mode structure evolution of a modeless multiwavelength Raman fiber laser.

Optics letters·2025
Same author

Simulation and Modelling of C+L+S Multiband Optical Transmission for the OCATA Time Domain Digital Twin.

Sensors (Basel, Switzerland)·2025

Related Experiment Video

Updated: Sep 22, 2025

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

672

Experimental implementation of a neural network optical channel equalizer in restricted hardware using pruning and

Diego Argüello Ron1, Pedro J Freire2,3, Jaroslaw E Prilepsky2

  • 1Aston Institute of Photonic Technologies, Aston University, Birmingham, B4 7ET, UK. d.arguelloron@aston.ac.uk.

Scientific Reports
|May 24, 2022
PubMed
Summary

Researchers reduced the complexity of artificial neural networks (NNs) for optical communication systems by applying pruning and quantization. This significantly cuts memory and computational load for NN-based equalizers on edge devices without performance loss.

More Related Videos

Quantum State Engineering of Light with Continuous-wave Optical Parametric Oscillators
09:23

Quantum State Engineering of Light with Continuous-wave Optical Parametric Oscillators

Published on: May 30, 2014

14.6K
Quasi-light Storage for Optical Data Packets
07:45

Quasi-light Storage for Optical Data Packets

Published on: February 6, 2014

11.0K

Related Experiment Videos

Last Updated: Sep 22, 2025

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

672
Quantum State Engineering of Light with Continuous-wave Optical Parametric Oscillators
09:23

Quantum State Engineering of Light with Continuous-wave Optical Parametric Oscillators

Published on: May 30, 2014

14.6K
Quasi-light Storage for Optical Data Packets
07:45

Quasi-light Storage for Optical Data Packets

Published on: February 6, 2014

11.0K

Area of Science:

  • Optical Communications
  • Artificial Intelligence
  • Edge Computing

Background:

  • Artificial neural networks (NNs) are crucial for next-gen optical communication equalizers.
  • High computational complexity of NNs hinders deployment on edge devices.
  • Reducing NN complexity is vital for practical hardware implementation.

Purpose of the Study:

  • To reduce the complexity of NN-based optical channel equalizers for edge computing.
  • To maintain acceptable performance after complexity reduction.
  • To analyze the computational complexity and hardware impact of compressed NN equalizers.

Main Methods:

  • Applied pruning and quantization techniques to a multi-layer perceptron (MLP) NN equalizer.
  • Simulated 30 GBd 1000 km standard single-mode fiber transmission.
  • Defined computational complexity in digital signal processing (DSP) terms.
  • Evaluated power consumption and latency on Raspberry Pi 4 and Nvidia Jetson Nano.

Main Results:

  • Achieved up to 87.12% memory reduction and 78.34% complexity reduction.
  • No noticeable performance degradation observed.
  • Quantified computational complexity and analyzed hardware performance impacts.

Conclusions:

  • Pruning and quantization effectively reduce NN equalizer complexity for edge deployment.
  • The developed technique is experimentally verified on edge hardware.
  • This approach enables efficient NN-based optical channel equalization in real-world systems.