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

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...
Second-order Op Amp Circuits01:19

Second-order Op Amp Circuits

Implementing second-order low-pass filters in audio systems is crucial in refining audio signals by eliminating undesirable high-frequency noise. These filters typically involve second-order op-amp circuits configured as voltage followers, encompassing two nodes with distinct storage elements.
The analysis of such circuits follows a systematic approach, similar to the second-order RLC circuits. In practical scenarios, bulky inductors are rarely employed due to their size and weight. This means...
Second Order systems II01:18

Second Order systems II

In an underdamped second-order system, where the damping ratio ζ is between 0 and 1, a unit-step input results in a transfer function that, when transformed using the inverse Laplace method, reveals the output response. The output exhibits a damped sinusoidal oscillation, and the difference between the input and output is termed the error signal. This error signal also demonstrates damped oscillatory behavior. Eventually, as the system reaches a steady state, the error diminishes to zero.
If  ζ...
Second Order systems I01:20

Second Order systems I

A servo system exemplifies a second-order system, featuring a proportional controller and load elements that ensure the output position aligns with the input position. The relationship between these components is described by a second-order differential equation. Applying the Laplace transform under zero initial conditions yields the transfer function, showing how inputs are converted to outputs in the system.
By reinterpreting the system, one can derive the closed-loop transfer function, which...
Fast Decoupled and DC Powerflow01:24

Fast Decoupled and DC Powerflow

The fast decoupled power flow method addresses contingencies in power system operations, such as generator outages or transmission line failures. This method provides quick power flow solutions, essential for real-time system adjustments. Fast decoupled power flow algorithms simplify the Jacobian matrix by neglecting certain elements, leading to two sets of decoupled equations:
Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model01:13

Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model

Drugs administered through various routes can lead to nonlinear elimination, resulting in complex pharmacokinetic behaviors crucial to understanding efficacious drug dosing.
When a drug is administered through a constant intravenous infusion and eliminated via nonlinear pharmacokinetics, it follows zero-order input. For example, oral drugs undergo first-order absorption upon administration and are eliminated through nonlinear pharmacokinetics.
In the case of subcutaneously administered drugs,...

You might also read

Related Articles

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

Sort by
Same author

Automated identification of cancerous smears using various competitive intelligent techniques.

Oncology reports·2006
Same author

A dynamical model for the analysis and acceleration of learning in feedforward networks.

Neural networks : the official journal of the International Neural Network Society·2001
Same author

Efficient perceptron learning using constrained steepest descent.

Neural networks : the official journal of the International Neural Network Society·2000
Same author

An efficient constrained training algorithm for feedforward networks.

IEEE transactions on neural networks·1995
Same author

Translation, rotation, and scale invariant pattern recognition by high-order neural networks and moment classifiers.

IEEE transactions on neural networks·1992

Related Experiment Video

Updated: Jul 7, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Two highly efficient second-order algorithms for training feedforward networks.

N Ampazis1, S J Perantonis

  • 1Inst. of Informatics and Telecommun., Nat. Center for Sci. Res. "DEMOKRITOS", Athens, Greece.

IEEE Transactions on Neural Networks
|February 5, 2008
PubMed
Summary

Two novel second-order algorithms enhance multilayer feedforward neural network training. These methods, incorporating adaptive momentum, outperform standard techniques like the Levenberg-Marquardt method in complex scenarios.

Related Experiment Videos

Last Updated: Jul 7, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Multilayer feedforward neural networks are crucial for complex pattern recognition.
  • Training these networks efficiently, especially for difficult problems, remains a significant challenge.
  • Existing second-order methods, including the Levenberg-Marquardt algorithm, can struggle with convergence in certain scenarios.

Purpose of the Study:

  • To introduce two novel, highly efficient second-order algorithms for training multilayer feedforward neural networks.
  • To address the limitations of existing training methods in handling complex optimization landscapes.
  • To demonstrate superior performance compared to standard second-order techniques.

Main Methods:

  • Development of two second-order algorithms based on Levenberg-Marquardt iterations.
  • Inclusion of an adaptive momentum term derived from a constrained optimization formulation.
  • Implementation requiring minimal additional computation over standard Levenberg-Marquardt iterations.

Main Results:

  • The proposed algorithms demonstrate high efficiency in training neural networks.
  • Simulations on large-scale neural network benchmarks show successful convergence in difficult problems.
  • The new methods outperform standard second-order techniques, including the Levenberg-Marquardt algorithm, which failed to converge.

Conclusions:

  • The developed algorithms offer a powerful and efficient solution for training complex neural networks.
  • These methods provide a significant advancement over existing second-order training techniques.
  • The adaptive momentum term is key to achieving robust convergence in challenging training scenarios.