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

Propagation of Action Potentials

Propagation of Action Potentials

The propagation of an action potential refers to the process by which a nerve impulse, or "action potential," travels along a neuron.
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...

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.

Linearization and Approximation

Linearization and Approximation

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...

Newton’s Method

Newton’s Method

Newton’s Method is a powerful iterative technique for approximating the roots of real-valued, differentiable functions, particularly when analytical solutions are impractical. This approach is widely used in scientific computing, engineering, and finance, where equations may be too complex for traditional algebraic methods to handle. The method relies on an iterative process that refines an initial estimate using the function’s derivative to approach the true solution progressively.

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...

Derivatives

Derivatives

DerivativesThe concept of instantaneous rate of change is fundamental in both mathematics and physics, particularly in describing how a moving object alters its position with respect to time. This rate is captured mathematically through the derivative of a function. The derivative at a point represents the slope of the tangent line to the curve of the function at that point and quantifies how the function’s output changes per infinitesimal change in input.Derivative of the Square Root...

You might also read

Related Articles

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

Sort by

Same author

Continuous mark-release recapture to improve estimates of movement and survival of the African malaria mosquitoes.

bioRxiv : the preprint server for biology·2026

Same author

Correlation of brain injury biomarkers with brain dysfunction, brain injury, and outcomes in critically ill patients: a post hoc exploratory analysis.

Infection·2026

Same author

Pathogens spread by high-altitude windborne mosquitoes.

bioRxiv : the preprint server for biology·2025

Same author

All optical neural interfaces.

Applied optics·2024

Same author

Urban malaria may be spreading via the wind-here's why that's important.

Proceedings of the National Academy of Sciences of the United States of America·2023

Same author

Continuous table tennis is associated with processing in frontal brain areas: an EEG approach.

Experimental brain research·2022

Search research articles

Related Experiment Videos

Nonlinear backpropagation: doing backpropagation without derivatives of the activation function.

J Hertz¹, A Krogh, B Lautrup

¹Nordita, Copenhagen.

IEEE Transactions on Neural Networks

|January 1, 1997

Summary

This study introduces a nonlinear backpropagation algorithm, eliminating the need for activation function derivatives. This innovation is ideal for hardware neural network processors and analog very large scale integration (VLSI) electronics.

Related Experiment Videos

Area of Science:

Artificial Intelligence
Machine Learning
Computational Neuroscience

Background:

Traditional backpropagation relies on derivative calculations for activation functions.
This dependency poses challenges for efficient hardware implementation of neural networks.
Exploring alternative algorithms is crucial for advancing neural processing hardware.

Purpose of the Study:

To develop and present a nonlinear backpropagation algorithm.
To demonstrate its applicability in feedforward networks.
To discuss its potential for analog very large scale integration (VLSI) hardware.

Main Methods:

Derivation of nonlinear backpropagation algorithms within the recurrent backpropagation framework.
Numerical simulations of feedforward networks using the proposed algorithm.
Analysis of implementation possibilities in analog VLSI circuits.

Main Results:

The nonlinear backpropagation algorithm successfully avoids the need for activation function derivatives.
Simulations on the NetTalk problem show the algorithm's effectiveness for feedforward networks.
The approach is compatible with hardware realizations, particularly analog VLSI.

Conclusions:

Nonlinear backpropagation offers a viable alternative to conventional methods, especially for hardware applications.
The algorithm's derivative-free nature simplifies hardware design and potentially improves efficiency.
This work paves the way for more practical and efficient neural processing hardware.