Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Multivariable Functions and Higher Derivatives

Multivariable Functions and Higher Derivatives

A multivariable function assigns a single output value to each ordered set of independent inputs, thereby defining a surface in three-dimensional space. For a function f(x, y), each point (x, y) corresponds to a height z = f(x, y). This geometric interpretation allows systematic analysis of how the output varies as multiple variables change simultaneously. Such functions frequently arise in physical models and optimization problems, where system behavior depends on several interacting...

Multi-input and Multi-variable systems

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...

Derivatives of Inverse Trigonometric Functions

Derivatives of Inverse Trigonometric Functions

A ship tracking an approaching aircraft relies on geometric measurements to find out the aircraft’s position relative to the observer. By measuring the slant distance to the aircraft and the angle of elevation, the horizontal and vertical components of the distance can be obtained using trigonometric relationships. This geometric approach provides a basis for analyzing how the observed angle changes as the aircraft moves closer to the ship.To examine the mathematical behavior of the angle of...

Linear Approximation in Frequency Domain

Linear Approximation in Frequency Domain

Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear.

Continuity for Functions of Multiple Variables

Continuity for Functions of Multiple Variables

Continuity in multivariable functions extends the concept familiar from single-variable calculus into higher dimensions, where a function's output depends on two or more input variables. This generalization is crucial in modeling real-world phenomena across spatial domains. A multivariable function is considered continuous at a point if three conditions are simultaneously satisfied: the function is defined at that point, the limit of the function exists as the input approaches the point from...

State Function, Exact and Inexact Differentials

State Function, Exact and Inexact Differentials

A state function is a thermodynamic property that depends solely on the current state of a system, irrespective of its history or how it arrived at that state. These functions are represented by capital letters, such as U, H, and S, which stand for internal energy, enthalpy, and entropy, respectively.For instance, the value of internal energy depends on the system's state variables and remains unaffected by the process path. This means that whether the system underwent a linear process or a...

You might also read

Related Articles

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

Sort by

Same author

Phase II study of trastuzumab-pkrb plus gedatolisib in patients with HER2-positive metastatic breast cancer who progressed after two or more HER2-directed therapies.

ESMO open·2026

Same author

First Measurement of Missing Energy due to Nuclear Effects in Monoenergetic Neutrino Charged-Current Interactions.

Physical review letters·2025

Same author

A kalihinol analog disrupts apicoplast function and vesicular trafficking in <i>P. falciparum</i> malaria.

Science (New York, N.Y.)·2024

Same author

A Potent Kalihinol Analogue Disrupts Apicoplast Function and Vesicular Trafficking in <i>P. falciparum</i> Malaria.

bioRxiv : the preprint server for biology·2023

Same author

Association of body mass index and bloodstream infections in patients on extracorporeal membrane oxygenation: a single-centre, retrospective, cohort study.

The Journal of hospital infection·2023

Same author

Impact of tuberculosis on the incidence of osteoporosis and osteoporotic fractures: a nationwide population-based cohort study.

Public health·2023

Search research articles

Related Experiment Videos

Sensitivity analysis of multilayer perceptron with differentiable activation functions.

J Y Choi¹, C H Choi

¹Dept. of Control and Instrum. Eng., Seoul Nat. Univ.

IEEE Transactions on Neural Networks

|January 1, 1992

Summary

This study introduces a new method to measure neural network sensitivity to weight changes. This helps in selecting stable network weights and predicting output variations for improved reliability.

Related Experiment Videos

Area of Science:

Artificial Intelligence
Machine Learning
Neural Networks

Background:

Multiple sets of connection weights in neural networks can achieve similar input-output mappings.
The sensitivity of a neural network's output to changes in its weights varies significantly with different weight sets.
Measuring this sensitivity is crucial for selecting robust weights and estimating output perturbations.

Purpose of the Study:

To propose a novel method for quantifying neural network sensitivity.
To develop formulas for calculating sensitivity based on weight and input perturbations.
To extend the sensitivity concept for broader applicability across different neural network configurations.

Main Methods:

A sensitivity measure is proposed for single-output multilayer perceptrons (MLPs) with differentiable activation functions.
Formulas are derived to calculate sensitivity for additive/multiplicative weight perturbations and input perturbations.
The sensitivity concept is generalized to accommodate any input patterns and multiple-output MLPs.

Main Results:

The proposed sensitivity measure effectively quantifies the impact of weight variations.
Derived formulas allow for the computation of sensitivity under various perturbation scenarios.
The generalized sensitivity concept is applicable to diverse neural network architectures.

Conclusions:

The developed sensitivity measures provide a valuable tool for analyzing neural network robustness.
The theoretical framework is validated through computer simulations, showing good agreement for small perturbations.
This work contributes to the understanding and practical implementation of reliable neural networks.