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

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:
Survival Tree01:19

Survival Tree

Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a survival tree begins...
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...

You might also read

Related Articles

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

Sort by
Same author

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

IEEE transactions on neural networks·2008
Same author

Efficient information theoretic strategies for classifier combination, feature extraction and performance evaluation in improving false positives and false negatives for spam e-mail filtering.

Neural networks : the official journal of the International Neural Network Society·2005
Same author

On neural network techniques in the secure management of communication systems through improving and quality assessing pseudorandom stream generators.

Neural networks : the official journal of the International Neural Network Society·2003
Same author

CoLD: a versatile detection system for colorectal lesions in endoscopy video-frames.

Computer methods and programs in biomedicine·2003
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

Related Experiment Videos

An efficient constrained training algorithm for feedforward networks.

D A Karras1, S J Perantonis

  • 1Inst. of Inf. and Telecommun., Nat. Res. Centre, Athens.

IEEE Transactions on Neural Networks
|January 1, 1995
PubMed
Summary

A new algorithm enhances feedforward network training by incorporating desired learning properties. This method improves convergence, learning speed, and generalization compared to standard backpropagation, demonstrating superior performance.

Related Experiment Videos

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Feedforward networks require efficient training algorithms for optimal performance.
  • Standard training methods like backpropagation can suffer from slow convergence and poor generalization.
  • Minimizing mean square error is a common but sometimes insufficient training objective.

Purpose of the Study:

  • To introduce a novel algorithm that supplements feedforward network training.
  • To improve convergence, learning speed, and generalization properties of neural networks.
  • To address limitations of traditional training methods by incorporating specific learning conditions.

Main Methods:

  • Supplementing the training phase with conditions beyond mean square error minimization.
  • Utilizing these conditions to guide hidden unit activation, weight vector alignment, node elimination, and step size regulation.
  • Applying the algorithm to benchmark binary tasks and a large-scale Optical Character Recognition (OCR) problem.

Main Results:

  • The novel algorithm demonstrated superior performance in terms of convergence and learning speed on benchmark tasks.
  • Evaluation on an OCR problem indicated enhanced generalization capability.
  • Statistical significance confirmed the algorithm's advantage over backpropagation and its variants.

Conclusions:

  • The proposed algorithm offers significant improvements in training efficiency and network performance.
  • Incorporating specific learning conditions effectively enhances key properties like convergence and generalization.
  • This approach represents a promising advancement in training feedforward neural networks.