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

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...

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.

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...

Effects of feedback

Effects of feedback

Feedback in control systems plays a critical role in shaping various operational parameters, extending beyond simple error reduction to influence stability, bandwidth, gain, impedance, and sensitivity. Understanding these effects requires examining a basic feedback system characterized by defined input, output, error, and feedback signals.
Feedback significantly modifies the gain of a control system. The gain of a system without feedback is altered by a factor of one plus GH, where G represents...

You might also read

Related Articles

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

Sort by

Same author

Complexity and uncertainty in future food system transformation modelling.

Nature food·2025

Same author

The challenge of unprecedented floods and droughts in risk management.

Nature·2022

Same author

The sensitivity of simulated streamflow to individual hydrologic processes across North America.

Nature communications·2022

Same author

Great Lakes Runoff Intercomparison Project Phase 3: Lake Erie (GRIP-E).

Journal of hydrologic engineering·2021

Same author

Integrated modelling to assess the impacts of water stress in a transboundary river basin: Bridging local-scale water resource operations to a river basin economy.

The Science of the total environment·2021

Same author

Breaking through language barriers.

Science (New York, N.Y.)·2021

Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013

Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011

Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011

Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011

Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011

Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011

See all related articles

Search research articles

Related Experiment Videos

A new formulation for feedforward neural networks.

Saman Razavi¹, Bryan A Tolson

¹Department of Civil and Environmental Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada. ssrazavi@uwaterloo.ca

IEEE Transactions on Neural Networks

|August 24, 2011

Summary

This summary is machine-generated.

This study introduces a reformulated neural network (ReNN) with a new geometric interpretation, improving training efficiency and generalization. ReNN offers a less complex error surface, enhancing performance over traditional feedforward networks.

Related Experiment Videos

Area of Science:

Artificial Intelligence
Machine Learning
Computational Geometry

Background:

Feedforward neural networks are widely used for function approximation but suffer from training and generalization challenges due to their black-box nature.
Understanding the internal behavior and functional geometry of neural networks is crucial for improving their performance.
Traditional network parameters (weights and biases) offer limited interpretability and can lead to complex error surfaces.

Purpose of the Study:

To develop a geometrically interpretable framework for feedforward neural networks.
To introduce a reformulated neural network (ReNN) with a simplified error response surface.
To propose a novel regularization measure based on geometric interpretation to enhance generalization.

Main Methods:

A detailed interpretation of neural network functional geometry was developed.
A new set of variables and a reformulated neural network (ReNN) were proposed.
Derivative-based (backpropagation variation) and derivative-free optimization algorithms were employed for training.
A new geometric-based regularization measure was introduced.

Main Results:

ReNN demonstrated a less complex error response surface compared to traditional feedforward networks.
ReNN was trained more effectively and efficiently using both derivative-based and derivative-free methods.
The proposed regularization measure proved to be an effective indicator of network generalization ability.
Experimental results across multiple test problems validated the ReNN approach and regularization measure.

Conclusions:

The proposed geometrical interpretation provides a more effective and interpretable alternative to traditional network parameters.
ReNN offers significant advantages in training efficiency and generalization compared to standard feedforward neural networks.
The novel regularization measure effectively evaluates and improves neural network generalization, addressing key limitations in current models.