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

Region of Convergence of Laplace Tarnsform01:20

Region of Convergence of Laplace Tarnsform

1.4K
The Region of Convergence (ROC) is a fundamental concept in signal processing and system analysis, particularly associated with the Laplace transform. The ROC represents an area in the complex plane where the Laplace transform of a given signal converges, determining the transform's applicability and utility.
Consider a decaying exponential signal that begins at a specific time. When deriving its Laplace transform, the time-domain variable is replaced with a complex variable. This...
1.4K
Neural Circuits01:25

Neural Circuits

3.0K
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...
3.0K
Survival Tree01:19

Survival Tree

499
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...
499

You might also read

Related Articles

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

Sort by
Same author

Spurious valleys in the error surface of recurrent networks--analysis and avoidance.

IEEE transactions on neural networks·2009
Same author

Backpropagation algorithms for a broad class of dynamic networks.

IEEE transactions on neural networks·2007
Same author

Molecular dynamics investigations of the dissociation of SiO2 on an ab initio potential energy surface obtained using neural network methods.

The Journal of chemical physics·2006
Same author

Prediction of molecular-dynamics simulation results using feedforward neural networks: reaction of a C2 dimer with an activated diamond (100) surface.

The Journal of chemical physics·2005

Related Experiment Video

Updated: Apr 30, 2026

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

11.5K

Error surface of recurrent neural networks.

Manh Cong Phan, Martin T Hagan

    IEEE Transactions on Neural Networks and Learning Systems
    |May 9, 2014
    PubMed
    Summary

    Spurious valleys in recurrent neural network error surfaces hinder training. This study analyzes these valleys in general layered networks, offering insights to improve recurrent neural network training.

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Deep Learning

    Background:

    • Previous research identified spurious valleys in single-layer recurrent networks, complicating training.
    • These valleys present significant challenges for optimizing recurrent neural network (RNN) performance.

    Purpose of the Study:

    • To extend the analysis of spurious valleys to general layered digital dynamic networks.
    • To identify and characterize types of spurious valleys in complex RNN architectures.

    Main Methods:

    • Analysis of error surfaces in general layered digital dynamic networks.
    • Investigation of factors influencing spurious valley formation, specifically input sequences and network architecture.

    Main Results:

    Related Experiment Videos

    Last Updated: Apr 30, 2026

    Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
    11:18

    Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

    Published on: March 2, 2015

    11.5K
  • Two types of spurious valleys were identified in the error surfaces of general layered networks.
  • These valleys are independent of the network's desired output or task.
  • Valley characteristics are determined solely by the input sequence and network architecture.

    • Conclusions:

    • Understanding spurious valleys is crucial for improving RNN training.
    • The findings provide a basis for developing new training strategies for recurrent neural networks.