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

Calibration Curves: Linear Least Squares01:20

Calibration Curves: Linear Least Squares

4.1K
A calibration curve is a plot of the instrument's response against a series of known concentrations of a substance. This curve is used to set the instrument response levels, using the substance and its concentrations as standards. Alternatively, or additionally, an equation is fitted to the calibration curve plot and subsequently used to calculate the unknown concentrations of other samples reliably.
For data that follow a straight line, the standard method for fitting is the linear...
4.1K
Differential Leveling01:12

Differential Leveling

656
Differential leveling is a precise method in surveying used to determine the elevation difference between two points. Its primary goal is to establish accurate vertical measurements to create level surfaces or grade lines critical for designing and constructing infrastructures such as roads, bridges, and buildings.The procedure for differential leveling begins with setting up and leveling the instrument at a point where the benchmark can be seen. The level rod is held on the benchmark (BM), and...
656
Residuals and Least-Squares Property01:11

Residuals and Least-Squares Property

9.1K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
9.1K
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

284
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...
284
One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation01:24

One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation

1.1K
This lesson introduces two critical methods in pharmacokinetics, the Wagner-Nelson and Loo-Riegelman methods, used for estimating the absorption rate constant (ka) for drugs administered via non-intravenous routes. The Wagner-Nelson method relates ka to the plasma concentration derived from the slope of a semilog percent unabsorbed time plot. However, it is limited to drugs with one-compartment kinetics and can be impacted by factors like gastrointestinal motility or enzymatic degradation.
On...
1.1K
Linearization and Approximation01:26

Linearization and Approximation

3
Linearization is a mathematical technique used to approximate complex, nonlinear functions with simpler linear models in the vicinity of a chosen reference point. The method is based on the idea that, although a function may be difficult to evaluate exactly, its behavior near a specific input value can often be closely approximated by the tangent line at that point. This approach is particularly useful when small deviations from a known value are involved.Consider the square root function, for...
3

You might also read

Related Articles

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

Sort by
Same author

Preserving RNA quality when freezing of human milk samples must occur before extraction: Validation of methods utilized in a multi-center cohort study.

Journal of mammary gland biology and neoplasia·2026
Same author

Lactational Western-Style Fat Exposure in Mice Programs Metabolic Dysfunction-Associated Steatotic Liver Disease (MASLD) in Male Offspring.

Molecular nutrition & food research·2026
Same author

Oxytocin signaling in adipocytes is required for normal milk fat production.

Cell metabolism·2026
Same author

A Cambrian soft-bodied biota after the first Phanerozoic mass extinction.

Nature·2026
Same author

Advanced adaptive strategies in an ancestral body plan: insights from a 510-Ma-old leptomitid sponge.

Royal Society open science·2025
Same author

Efficient Enrichment of Docosahexaenoic Acid (DHA) in Mother's Milk and in the Brain and Retina of the Offspring by Lysophosphatidylcholine (LPC)-DHA in the Maternal Diet.

Nutrients·2025

Related Experiment Video

Updated: Jan 14, 2026

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
06:45

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Published on: October 28, 2022

2.1K

BDS-Adam optimizer integrating adaptive variance rectification with semi-adaptive gradient smoothing.

Yichuan Shao1, Shiqian Weng1, Haijing Sun1

  • 1School of Intelligent Science and Information Engineering, Shenyang University, Shenyang, 110044, China.

Scientific Reports
|October 22, 2025
PubMed
Summary

A new optimizer, BDS-Adam, enhances deep learning training by fixing biased gradients and improving stability. This adaptive method boosts convergence speed and model accuracy on diverse datasets.

Keywords:
Adaptive optimizerConvergence analysisDeep learningGradient smoothingVariance correction

More Related Videos

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.6K

Related Experiment Videos

Last Updated: Jan 14, 2026

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
06:45

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Published on: October 28, 2022

2.1K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.6K

Area of Science:

  • Machine Learning
  • Deep Learning Optimization
  • Gradient-Based Optimization

Background:

  • The Adam optimizer suffers from biased gradient estimation and early-stage training instability.
  • These limitations hinder optimal performance in deep learning models.

Purpose of the Study:

  • Introduce BDS-Adam, an enhanced Adam optimizer variant.
  • Address biased gradients and improve training stability for deep learning.

Main Methods:

  • Implemented a dual-path framework with nonlinear gradient mapping and semi-adaptive gradient smoothing.
  • Utilized gradient fusion and adaptive second-order moment correction.
  • Conducted convergence analysis under non-convex settings.

Main Results:

  • BDS-Adam demonstrated improved robustness and long-term stability.
  • Achieved test accuracy increases of 9.27% (CIFAR-10), 0.08% (MNIST), and 3.00% (gastric pathology dataset) over Adam.
  • Empirical evaluations confirmed enhanced convergence speed and generalization.

Conclusions:

  • BDS-Adam effectively overcomes Adam's limitations.
  • The proposed optimizer enhances both convergence and generalization across various tasks.
  • BDS-Adam offers a more stable and accurate training alternative.