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

Gradient Vectors and Their Applications01:19

Gradient Vectors and Their Applications

Every point on a topographical map corresponds to a particular elevation, so the landscape can be modeled as a surface whose height depends on horizontal position. From any given location, a hiker may face infinitely many directions, but only one direction produces the fastest possible increase in elevation. This unique route is called the direction of steepest ascent, and in multivariable calculus, it is represented by the gradient vector of the elevation function.The gradient vector points...
Maximizing the Directional Derivative01:25

Maximizing the Directional Derivative

The directional derivative is a central concept in multivariable calculus that describes how a function changes at a given point when moving in a specified direction. This direction is represented by a unit vector, ensuring that only the orientation influences the rate of change. By varying the direction, different rates of change can be observed, demonstrating that the directional derivative depends strongly on the chosen direction.The directional derivative is computed using the gradient...
Significance of the Gradient Vector01:27

Significance of the Gradient Vector

A surface defined by a function of two variables can be understood by examining how it changes along specific directions. When one variable is held constant, the surface reduces to a curve that reflects variation in the other variable. For example, fixing one variable and moving parallel to a coordinate axis produces a cross-sectional curve. The slope of this curve at a given point represents how the function changes in that particular direction, providing a measure of local steepness.By...
Linear Approximation in Time Domain01:21

Linear Approximation in Time Domain

Nonlinear systems often require sophisticated approaches for accurate modeling and analysis, with state-space representation being particularly effective. This method is especially useful for systems where variables and parameters vary with time or operating conditions, such as in a simple pendulum or a translational mechanical system with nonlinear springs.
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length, the...
Basic Discrete Time Signals01:16

Basic Discrete Time Signals

The unit step sequence is defined as 1 for zero and positive values of the integer n. This sequence can be graphically displayed using a set of eight sample points, showing a step function starting from n=0 and remaining constant thereafter.
The unit impulse or sample sequence is mathematically expressed as zero for all n values except at n=0, where it is one. The unit impulse sequence, denoted by δ(n), is the first difference of the unit step sequence, while the unit step sequence u(n) is the...

You might also read

Related Articles

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

Sort by
Same author

Design of a Wobble-Scheme Heterojunction for Catalytic Cancer Therapy.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Ice-water sheet coverage for rapid core temperature reduction in exertional heat stroke: A case series.

The American journal of emergency medicine·2026
Same author

Atractylenolide I Alleviates Lipotoxicity in Hepatocytes and Protects NAFLD in Mice Through SIRT1-Dependent IRE1α-XBP1 Pathway.

Phytotherapy research : PTR·2026
Same author

Abietic acid targets RAN to restrict coxsackievirus B3 infection.

Frontiers in microbiology·2026
Same author

Discovery and characterization of hinokiflavone as a potent natural CD137 inhibitor for Kawasaki disease.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026
Same author

Exosomal miR-181d-5p derived from distal airway stem cells inhibit apoptosis of pulmonary vascular endothelial cells in COPD mice by targeting PDAP1.

Stem cell research & therapy·2026

Related Experiment Video

Updated: Jun 28, 2026

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Robust adaptive gradient-descent training algorithm for recurrent neural networks in discrete time domain.

Qing Song1, Yilei Wu, Yeng Chai Soh

  • 1School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798, Singapore. eqsong@ntu.edu.sg

IEEE Transactions on Neural Networks
|November 8, 2008
PubMed
Summary

This study introduces a Robust Adaptive Gradient-Descent (RAGD) algorithm to improve recurrent neural network (RNN) training. RAGD optimizes training speed and weight convergence for real-time signal processing.

Related Experiment Videos

Last Updated: Jun 28, 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
  • Signal Processing

Background:

  • Recurrent Neural Networks (RNNs) face challenges with transient response in real-time applications.
  • Conventional training algorithms like Backpropagation Through Time (BPTT) and Real-Time Recurrent Learning (RTRL) exhibit slow convergence.
  • High learning rates can lead to unstable training and weight divergence in RNNs.

Purpose of the Study:

  • To develop an optimal tradeoff between RNN training speed and weight convergence.
  • To introduce a novel hybrid training concept for RNNs.
  • To enhance the performance of RNNs in real-time signal processing.

Main Methods:

  • Development of a Robust Adaptive Gradient-Descent (RAGD) training algorithm.
  • Hybrid training approach switching between online Backpropagation (BP) and RTRL based on stability conditions.
  • Application of the conic sector theorem to derive weight convergence and L(2)-stability.

Main Results:

  • The RAGD algorithm achieves optimized adaptive learning, maximizing RNN training speed.
  • Stability and convergence criteria are maintained without violating them.
  • Computer simulations validate the theoretical results and demonstrate practical applicability.

Conclusions:

  • The RAGD algorithm effectively addresses the transient response issue in RNNs.
  • It provides a superior balance between training speed and weight convergence compared to conventional methods.
  • The RAGD algorithm is suitable for real-time signal processing applications requiring stable and fast RNN training.