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

Search research articles

Related Experiment Videos

Analog neural nonderivative optimizers.

M M Teixeira¹, S H Zak

¹Department of Electrical Engineering, FEIS/UNESP, 15385-000-Ilha Solteira-SP, Brazil.

IEEE Transactions on Neural Networks

|February 7, 2008

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Acute murine-betacoronavirus infection impairs testicular steroidogenesis and the quality of sperm production.

Journal of reproductive immunology·2024

Same author

Neutrophil activity in sepsis: a systematic review.

Brazilian journal of medical and biological research = Revista brasileira de pesquisas medicas e biologicas·2020

Same author

Short-chain fatty acids and FFAR2 as suppressors of bone resorption.

Bone·2019

Same author

Evaluation of the effects of extracts of Maytenus imbricata (Celastraceae) on the treatment of inflammatory and metabolic dysfunction induced by high-refined carbohydrate diet.

Inflammopharmacology·2018

Same author

Plasma levels of innate immune mediators are associated with liver fibrosis in low parasite burden Schistosoma mansoni-infected individuals.

Scandinavian journal of immunology·2018

Same author

Exploring the genomic diversity of black yeasts and relatives (<i>Chaetothyriales</i>, <i>Ascomycota</i>).

Studies in mycology·2017

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

New continuous-time neural networks solve convex nonlinear programming problems without gradient information. These nonderivative optimizers offer a robust, hardware-implementable solution for single and multi-variable optimization tasks.

Area of Science:

* Computational Neuroscience
* Optimization Theory
* Machine Learning

Background:

* Gradient-based optimization methods are standard but can be computationally intensive or inapplicable when gradients are unavailable.
* Continuous-time neural networks offer a biologically plausible framework for dynamic computational tasks.
* Unconstrained nonlinear programming problems are fundamental in various scientific and engineering domains.

Purpose of the Study:

* To propose and analyze novel continuous-time neural networks for solving convex nonlinear unconstrained programming problems.
* To develop nonderivative optimization methods that do not require gradient information of the objective function.
* To design networks that are robust, easily implementable in hardware, and scalable to multi-variable problems.

Main Methods:

Related Experiment Videos

* Development of continuous-time neural network architectures for one-dimensional optimization.
* Analysis of an existing one-dimensional optimizer and proposal of a new line search optimizer.
* Extension of one-dimensional networks to multidimensional networks using a coordinate descent approach.

Main Results:

* Proposed networks function as nonderivative optimizers for convex nonlinear programming.
* The new one-dimensional optimizer exhibits robustness and disturbance rejection properties.
* Hardware implementation using standard circuit elements is feasible.
* Multidimensional networks effectively implement a continuous coordinate descent method.

Conclusions:

* Continuous-time neural networks provide an effective nonderivative approach for convex nonlinear unconstrained optimization.
* The proposed networks are robust, hardware-friendly, and scalable, offering a practical alternative to gradient-based methods.
* This work contributes to the intersection of neural networks, optimization, and hardware implementation.