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

Neural Circuits01:25

Neural Circuits

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...
Classification of Systems-II01:31

Classification of Systems-II

Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
Classification of Systems-I01:26

Classification of Systems-I

Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Neuroplasticity01:01

Neuroplasticity

Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.

You might also read

Related Articles

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

Sort by
Same author

A growing and pruning method for radial basis function networks.

IEEE transactions on neural networks·2009
Same author

Imaging after urinary tract infection in male neonates.

Pediatrics·2000
Same author

The etiology of renal scars in infants with pyelonephritis and vesicoureteral reflux.

Pediatric nephrology (Berlin, Germany)·2000
Same author

Sodium potassium adenosine triphosphatase activity in preterm and term infants and its possible role in sodium homeostasis during maturation.

Archives of disease in childhood. Fetal and neonatal edition·1999
Same author

Neutropenia as a complication of intravenous immunoglobulin (IVIG) therapy in children with immune thrombocytopenic purpura: common and non-alarming.

International journal of immunopharmacology·1999
Same author

Clinical relevance of therapeutic drug monitoring of digoxin and gentamicin in the saliva of children.

Therapeutic drug monitoring·1998

Related Experiment Videos

Recursive training of neural networks for classification.

M Aladjem1

  • 1Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev, 84105 Beer-Sheva, Israel. aladjem@ee.bgu.ac.il

IEEE Transactions on Neural Networks
|February 6, 2008
PubMed
Summary

This study introduces a novel recursive training method for neural networks. The approach helps classification models escape local minima, improving solutions for complex data and character recognition tasks.

Related Experiment Videos

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computer Vision

Background:

  • Neural network training often gets stuck in local minima of the error function, hindering optimal classification performance.
  • Existing methods may struggle to find global optima, limiting model accuracy.

Purpose of the Study:

  • To propose a novel recursive training method for neural networks designed for classification tasks.
  • To address the challenge of local minima in neural network training.

Main Methods:

  • The proposed method involves searching for discriminant functions associated with local error function minima.
  • It utilizes a data transformation technique to create new training data with a deflated error function minimum.
  • Iterative application of this transformation guides the optimizer toward new solutions.

Main Results:

  • Simulation studies and a character recognition application demonstrated the method's effectiveness.
  • The approach successfully escaped local minima, leading to improved solutions.
  • The recursive strategy directed the local optimizer to explore new areas of the error function landscape.

Conclusions:

  • The novel recursive training method offers a promising approach to overcome local minima in neural network classification.
  • This technique enhances the ability of neural networks to find better solutions, particularly in applications like character recognition.