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

Root Loci for Positive-Feedback Systems

Root Loci for Positive-Feedback Systems

The Hartley oscillator is a positive feedback system that sustains oscillations by feeding the output back to the input in phase, thereby reinforcing the signal. Positive feedback systems can be viewed as negative feedback systems with inverted feedback signals. In these systems, the root locus encompasses all points on the s-plane where the angle of the system transfer function equals 360 degrees.
The construction rules for the root locus in positive feedback systems are similar to those in...

Neural Circuits

Neural Circuits

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...

Feedback control systems

Feedback control systems

Feedback control systems are categorized in various ways based on their design, analysis, and signal types.
Linear feedback systems are theoretical models that simplify analysis and design. These systems operate under the principle that their output is directly proportional to their input within certain ranges. For instance, an amplifier in a control system behaves linearly as long as the input signal remains within a specific range. However, most physical systems exhibit inherent nonlinearity...

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.

Neural Regulation

Neural Regulation

Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.

Positive and Negative Feedback Loops

Positive and Negative Feedback Loops

Animal organs and organ systems constantly adjust to internal and external changes through a process called homeostasis ("steady state"). Examples of these changes include regulation of the level of glucose or calcium in the blood or internal responses to external temperatures. Homeostasis requires maintaining an internal dynamic equilibrium:

You might also read

Related Articles

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

Sort by

Same author

Effects of potassium fertilizer application on <i>Qiongzhuea tumidinod</i> shoots nutritional quality and soil nutrients.

Frontiers in plant science·2025

Same author

Dynamic conditional survival nomogram for primary hepatocellular carcinoma: a population-based analysis.

Discover oncology·2025

Same author

Molecular Dynamics Simulation of the Three-Phase Equilibrium Line of CO<sub>2</sub> Hydrate with OPC Water Model.

ACS omega·2023

Same author

Experimental apparatus for resistivity measurement of gas hydrate-bearing sediment combined with x-ray computed tomography.

The Review of scientific instruments·2022

Same author

The performance of OPC water model in prediction of the phase equilibria of methane hydrate.

The Journal of chemical physics·2022

Same author

Neural belief network.

Neural networks : the official journal of the International Neural Network Society·2009

Search research articles

Related Experiment Videos

Local coupled feedforward neural network.

¹Computation Center, Harbin University of Science and Technology, No. 52, Xuefu Road, Harbin, PR China. sun_jianye@yahoo.com

Neural Networks : the Official Journal of the International Neural Network Society

|July 15, 2009

Summary

A new local coupled feedforward neural network activates only nearby hidden nodes for faster processing. This model demonstrates universal approximation and enables knowledge accumulation in neural networks.

Related Experiment Videos

Area of Science:

Artificial Intelligence
Machine Learning
Computational Neuroscience

Background:

Multilayer Perceptrons (MLPs) are foundational feedforward neural networks.
Efficient training and knowledge accumulation in MLPs remain areas of research.
The computational cost of traditional neural networks can be high.

Purpose of the Study:

To introduce a novel neural network architecture: the local coupled feedforward neural network.
To analyze the theoretical properties and practical performance of this new network.
To explore the potential for enhanced learning and knowledge accumulation.

Main Methods:

Designed a neural network with a connection structure similar to MLPs with one hidden layer.
Implemented a local coupling mechanism where each hidden node has an input space address.
Activated only the hidden nodes nearest to the input during forward and backward propagation.

Main Results:

Theoretical analysis confirmed the 'universal approximation' property of the local coupled network.
Simulation results demonstrated its capability to solve feedforward neural network learning problems.
The local coupling characteristic was shown to facilitate knowledge accumulation.

Conclusions:

The local coupled feedforward neural network offers an efficient alternative to traditional MLPs.
This architecture possesses strong theoretical learning capabilities, including universal approximation.
The localized processing enables a unique advantage for incremental learning and knowledge storage.