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

PI Controller: Design

PI Controller: Design

Proportional Integral (PI) controllers are a fundamental component in modern control systems, widely used to enhance performance and mitigate steady-state errors. They are particularly effective in applications such as automatic brightness adjustment on smartphones, where they excel at mitigating steady-state errors for step-function inputs. Unlike PD controllers, which require time-varying errors to function optimally, PI controllers leverage their integral component to address residual...

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.

Application of Nonlinear Inequalities

Application of Nonlinear Inequalities

A nonlinear inequality describes a comparison involving an expression that curves or behaves more complexly than a straight line. These inequalities often appear in forms that include squares, products, or variables in the denominator.To solve such an inequality, one starts by rewriting it so that zero appears on one side. For example, the inequality: can be factored as: This form makes it easier to identify the values that cause the expression to equal zero. In this case, the key values are 3...

Quadratic Models

Quadratic Models

Quadratic models are mathematical representations used to describe relationships in which the rate of change changes at a constant rate. These models appear in a wide variety of natural and engineered systems, especially those involving motion, forces, and optimization. One common application is analyzing the vertical motion of objects influenced by gravity, such as a ball thrown into the air.In such scenarios, the object's height changes over time in a curved pattern, rising to a maximum point...

Open and closed-loop control systems

Open and closed-loop control systems

Control systems are foundational elements in automation and engineering. They are broadly categorized into open-loop and closed-loop systems. These classifications hinge on the presence or absence of feedback mechanisms, significantly influencing the system's performance, complexity, and application.
An open-loop control system operates without feedback from the output. It consists of two primary elements: the controller and the controlled process. The controller receives an input signal and...

Lagrange Multipliers: Two Constraints

Lagrange Multipliers: Two Constraints

The method of Lagrange multipliers with two constraints is used to optimize a function subject to two independent constraints. In many applications, the objective function represents a quantity to be maximized or minimized, such as cost, area, distance, or energy. The two constraints represent requirements that the solution must satisfy, such as fixed volume, limited resources, or prescribed dimensions.For a function of three variables, each constraint forms a surface in three-dimensional space.

You might also read

Related Articles

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

Sort by

Same author

Identifying the Neural Correlates of Resting State Affect Processing Dynamics.

Frontiers in neuroimaging·2023

Same author

Smartphone intervention to optimize medication-assisted treatment outcomes for opioid use disorder: study protocol for a randomized controlled trial.

Trials·2023

Same author

Workshops of the Eighth International Brain-Computer Interface Meeting: BCIs: The Next Frontier.

Brain computer interfaces (Abingdon, England)·2023

Same author

Smartphone intervention to optimize medication assisted treatment outcomes for opioid use disorder: study protocol for a randomized controlled trial.

Research square·2023

Same author

Lessons learned: A neuroimaging research center's transition to open and reproducible science.

Frontiers in big data·2022

Same author

Action-value processing underlies the role of the dorsal anterior cingulate cortex in performance monitoring during self-regulation of affect.

PloS one·2022

Search research articles

Related Experiment Video

Updated: Jul 13, 2026

WheelCon: A Wheel Control-Based Gaming Platform for Studying Human Sensorimotor Control

WheelCon: A Wheel Control-Based Gaming Platform for Studying Human Sensorimotor Control

Published on: August 15, 2020

Robust reinforcement learning control using integral quadratic constraints for recurrent neural networks.

Charles W Anderson¹, Peter Michael Young, Michael R Buehner

¹Department of Computer Science, Colorado State University, Fort Collins, CO 80523-1873, USA. anderson@cs.colostate.edu

IEEE Transactions on Neural Networks

|August 3, 2007

Summary

This study ensures stability in machine learning feedback control systems. A novel method guarantees recurrent neural network (NN) stability during reinforcement learning, enabling reliable control system design.

Related Experiment Videos

Last Updated: Jul 13, 2026

WheelCon: A Wheel Control-Based Gaming Platform for Studying Human Sensorimotor Control

WheelCon: A Wheel Control-Based Gaming Platform for Studying Human Sensorimotor Control

Published on: August 15, 2020

Area of Science:

Control Systems Engineering
Machine Learning Theory
Artificial Intelligence

Background:

Machine learning (ML) in feedback control is hindered by a lack of stability guarantees.
Robust control theory provides stability analysis frameworks, but requires linear, time-invariant system representations.
The integral quadratic constraint (IQC) framework necessitates bounded gain for system components.

Purpose of the Study:

To analyze the stability of feedback control loops incorporating recurrent neural networks (NNs).
To develop a method for guaranteeing NN stability within control systems.
To demonstrate a learning algorithm that ensures stability during training.

Main Methods:

Nonlinear and time-varying components of NNs were replaced with IQCs on their gain.
Stability analysis was performed within the IQC framework.
A reinforcement learning algorithm was developed for NN training with stability guarantees.

Main Results:

A specific range of NN weights was identified, ensuring guaranteed stability.
The developed algorithm successfully trained recurrent NNs while maintaining stability.
The approach addresses the limitations of applying ML to control systems.

Conclusions:

The IQC framework can be extended to analyze and guarantee the stability of recurrent neural networks in feedback control.
This work provides a pathway for developing robust and stable ML-based control systems.
The demonstrated algorithm facilitates the practical implementation of stable learning control.