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

Propagation of Action Potentials01:23

Propagation of Action Potentials

15.7K
The propagation of an action potential refers to the process by which a nerve impulse, or "action potential," travels along a neuron.
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
15.7K
Neural Circuits01:25

Neural Circuits

3.3K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
3.3K
The Role of Ion Channels in Neuronal Computation01:19

The Role of Ion Channels in Neuronal Computation

4.3K
A postsynaptic neuron usually receives numerous impulses from several other presynaptic neurons. The axon hillock of the postsynaptic neuron integrates all these signals and determines the likelihood of firing an action potential.
Sometimes a single EPSP is strong enough to induce an action potential in the postsynaptic neuron. However, multiple presynaptic inputs must often create EPSPs around the same time for the postsynaptic neuron to be sufficiently depolarized to fire an action potential....
4.3K
Potential Due to a Polarized Object01:29

Potential Due to a Polarized Object

937
A neutral atom consists of a positively charged nucleus surrounded by a negatively charged electron cloud. When placed in an external electric field, the external electric force pulls the electrons and nucleus apart, opposite to the intrinsic attraction between the nucleus and the electrons. The opposing forces balance each other with a slight shift between the center of masses of the nucleus and the electron cloud, resulting in a polarized atom. On the other hand, a few molecules, like water,...
937
Graphs of Polar Equations01:17

Graphs of Polar Equations

435
The polar coordinate system represents points using a distance from a central point (the pole) and an angle from a reference direction (the polar axis). Unlike rectangular coordinates, polar coordinates are ideal for graphing curves with radial symmetry or periodic behavior.Some general forms of graphs in polar coordinates include the following:Equation of a Circle (Centered at the Pole):A graph where the radius remains constant for all angles traces a circle centered at the pole:Equation of a...
435
Dielectric Polarization in a Capacitor01:31

Dielectric Polarization in a Capacitor

6.7K
The presence of a dielectric medium in a capacitor not only changes the voltage and capacitance but also affects the electric field. In general, dielectrics can be of two types: polar and nonpolar. In a polar dielectric, the positive and negative charges in the molecules are separated by a distance and hence have a permanent dipole moment. In contrast, no such charge separation exists in a nonpolar dielectric, however the nonpolar molecules get polarized in the presence of an external electric...
6.7K

You might also read

Related Articles

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

Sort by
Same author

Sequential Learning on sEMGs in Short- and Long-term Situations via Self-training Semi-supervised Support Vector Machine.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2022
Same author

Hyperbolic Gradient Operator and Hyperbolic Back-Propagation Learning Algorithms.

IEEE transactions on neural networks and learning systems·2017
Same author

Resolution of Singularities Introduced by Hierarchical Structure in Deep Neural Networks.

IEEE transactions on neural networks and learning systems·2016
Same author

Performance Bounds of Quaternion Estimators.

IEEE transactions on neural networks and learning systems·2015
Same author

Local minima in hierarchical structures of complex-valued neural networks.

Neural networks : the official journal of the International Neural Network Society·2013
Same author

The uniqueness theorem for complex-valued neural networks with threshold parameters and the redundancy of the parameters.

International journal of neural systems·2008

Related Experiment Video

Updated: Apr 16, 2026

Real-time Electrophysiology: Using Closed-loop Protocols to Probe Neuronal Dynamics and Beyond
08:08

Real-time Electrophysiology: Using Closed-loop Protocols to Probe Neuronal Dynamics and Beyond

Published on: June 24, 2015

12.2K

Learning dynamics of a single polar variable complex-valued neuron.

Tohru Nitta1

  • 1National Institute of Advanced Industrial Science and Technology, Tsukuba, Ibaraki, 305-8568 Japan tohru-nitta@aist.go.jp.

Neural Computation
|March 17, 2015
PubMed
Summary

This study explores polar variable complex-valued neurons, revealing unidentifiable parameters that hinder learning speed and cause plateaus. Alternative methods like amplitude-phase error and natural gradient descent can mitigate these issues.

More Related Videos

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches
10:50

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

Published on: June 21, 2022

2.3K
Examining Local Network Processing using Multi-contact Laminar Electrode Recording
13:40

Examining Local Network Processing using Multi-contact Laminar Electrode Recording

Published on: September 8, 2011

13.3K

Related Experiment Videos

Last Updated: Apr 16, 2026

Real-time Electrophysiology: Using Closed-loop Protocols to Probe Neuronal Dynamics and Beyond
08:08

Real-time Electrophysiology: Using Closed-loop Protocols to Probe Neuronal Dynamics and Beyond

Published on: June 24, 2015

12.2K
Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches
10:50

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

Published on: June 21, 2022

2.3K
Examining Local Network Processing using Multi-contact Laminar Electrode Recording
13:40

Examining Local Network Processing using Multi-contact Laminar Electrode Recording

Published on: September 8, 2011

13.3K

Area of Science:

  • Computational Neuroscience
  • Machine Learning

Background:

  • Complex-valued neural networks offer advantages in signal processing.
  • Polar coordinate representation introduces unique learning dynamics.

Purpose of the Study:

  • Investigate the learning characteristics of polar variable complex-valued neurons.
  • Analyze the impact of unidentifiable parameters on learning.
  • Evaluate methods to overcome learning limitations.

Main Methods:

  • Computer simulations of a single polar variable complex-valued neuron.
  • Application of steepest gradient-descent with square error.
  • Comparison with steepest gradient-descent using amplitude-phase error and complex-valued natural gradient methods.

Main Results:

  • Polar variable complex-valued neurons exhibit unidentifiable parameters (singular points).
  • Steepest gradient-descent with square error leads to slow learning and plateau phenomena due to singular points.
  • Alternative error functions and training algorithms can reduce the impact of singular points.

Conclusions:

  • The learning dynamics of polar variable complex-valued neurons are sensitive to parameter identifiability.
  • Careful selection of error functions and training algorithms is crucial for effective learning.
  • Complex-valued natural gradient methods show promise in addressing learning challenges.