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 Uncertainty from Random Error00:59

Propagation of Uncertainty from Random Error

An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
Insensitive Nuclei Enhanced by Polarization Transfer (INEPT)01:15

Insensitive Nuclei Enhanced by Polarization Transfer (INEPT)

Insensitive Nuclei Enhanced by Polarization Transfer (INEPT) is an advanced Nuclear Magnetic Resonance (NMR) technique specifically designed to detect and enhance the signals of low-abundance nuclei, such as carbon-13 and nitrogen-15, in small molecules. The fundamental principle behind INEPT is the transfer of polarization from a more abundant and highly polarizable nucleus, typically hydrogen-1, to the low-abundance nucleus of interest. This process effectively boosts the NMR signal of the...
Propagation of Uncertainty from Systematic Error01:10

Propagation of Uncertainty from Systematic Error

The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this particular...
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Linear Approximations01:23

Linear Approximations

For a differentiable function of two variables, linear approximation estimates values near a known point by replacing the curved surface with its tangent plane. Consider the function\begin{equation*}f(x,y)=x^2+3y^2\end{equation*}near the point (2, 1). The exact value at this point is f(2, 1) = 22 + 3(1)2 = 4 + 3 = 7.The linear approximation of f(x, y)) near (a, b) is\begin{equation*}L(x,y)=f(a,b)+f_x(a,b)(x-a)+f_y(a,b)(y-b)\end{equation*}First, compute the partial derivatives: fx(x, y) = 2x and...
Plotting and Calibrating the Root Locus01:19

Plotting and Calibrating the Root Locus

Root loci often diverge as system poles shift from the real axis to the complex plane. Key points in this transition are the breakaway and break-in points, indicating where the root locus leaves and reenters the real axis. The branches of the root locus form an angle of 180/n degrees with the real axis, where n is the number of branches at a breakaway or break-in point.
The maximum gain occurs at the breakaway points between open-loop poles on the real axis, while the minimum gain is observed...

You might also read

Related Articles

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

Sort by
Same author

Correction: An exploratory study of behavioral traits and the establishment of social relationships in female laboratory rats.

PloS one·2026
Same author

Psychometric properties of hierarchical psychiatric symptoms on the general population.

PLOS mental health·2026
Same author

Exploratory responses of rats to cage-mates and conspecifics from another cage in a habituation-dishabituation paradigm with multiple habituation stimuli.

Behavioural processes·2026
Same author

Usage Styles of Physical Activity Apps are Associated with Long-Term Activity Levels: A 6-Month Prospective Analysis.

Inquiry : a journal of medical care organization, provision and financing·2026
Same author

Beyond dichotomy: Diversity of ultrasonic vocalizations in rats.

Behavioural brain research·2026
Same author

Domestication Effects on Immune Response: Comparison of Phytohemagglutinin-Induced Skin Swelling in Domesticated Bengalese Finch and Its Wild Ancestor, White-Rumped Munia.

Journal of experimental zoology. Part A, Ecological and integrative physiology·2026

Related Experiment Video

Updated: Jun 17, 2026

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
10:44

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Published on: December 7, 2021

Optimal node perturbation in linear perceptrons with uncertain eligibility trace.

Kentaro Katahira1, Tatsuya Cho, Kazuo Okanoya

  • 1Graduate School of Frontier Sciences, The University of Tokyo, Kashiwa, Chiba, Japan. katahira@mns.k.u-tokyo.ac.jp

Neural Networks : the Official Journal of the International Neural Network Society
|December 17, 2009
PubMed
Summary
This summary is machine-generated.

Node perturbation learning, a method for stochastic gradient descent in reinforcement learning, faces challenges with residual error. This study introduces an adaptive learning rule to balance robustness and error reduction for improved performance.

Related Experiment Videos

Last Updated: Jun 17, 2026

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
10:44

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Published on: December 7, 2021

Area of Science:

  • Machine Learning
  • Computational Neuroscience

Background:

  • Node perturbation learning is a gradient-free method applicable to reinforcement learning.
  • Conventional methods suffer from unaddressed residual errors post-convergence.
  • Infinitesimal perturbations reduce error but lack robustness against noise in eligibility traces.

Purpose of the Study:

  • To derive an optimal parameter schedule for node perturbation learning with linear perceptrons.
  • To address uncertainty and noise within the eligibility trace.
  • To develop an adaptive learning rule that optimizes the trade-off between robustness and residual error.

Main Methods:

  • Derivation of an optimal parameter schedule for node perturbation learning.
  • Analysis of linear perceptrons with uncertainty in the eligibility trace.
  • Development of an adaptive learning rule.

Main Results:

  • An adaptive learning rule was derived, effectively managing the trade-off between robustness to uncertainty and residual error reduction.
  • The proposed method enhances performance in scenarios with noisy eligibility traces.
  • Optimal parameter schedules were identified for improved learning stability.

Conclusions:

  • The derived adaptive learning rule offers a solution to limitations in conventional node perturbation learning.
  • This research provides a framework for designing more robust and accurate learning algorithms.
  • Findings contribute to understanding learning mechanisms and interpreting biological neural networks.