Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

154
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
154
Reinforcement Schedules01:24

Reinforcement Schedules

246
Positive reinforcement is a powerful method for teaching new behaviors to both animals and humans. B.F. Skinner demonstrated this with his experiments using rats in a Skinner box. When a rat pressed a lever, it received a food pellet. This immediate reward encouraged the rat to repeat the behavior. This method, where a reward follows every instance of the behavior, is known as continuous reinforcement. It is highly effective for establishing new behaviors quickly.
Once a behavior is learned,...
246
Reinforcement01:23

Reinforcement

383
Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:
383
Neural Circuits01:25

Neural Circuits

1.7K
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...
1.7K
Observational Learning01:12

Observational Learning

341
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
341
Neural Regulation01:37

Neural Regulation

40.4K
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.
40.4K

You might also read

Related Articles

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

Sort by
Same author

Cognitive Distinctions as a Language for Cognitive Science: Comparing Methods of Description in a Model of Referential Communication.

Artificial life·2025
Same author

Editorial Introduction to the 2023 Conference on Artificial Life Special Issue.

Artificial life·2025
Same author

The Dynamics of Social Interaction Among Evolved Model Agents.

Artificial life·2023
Same author

A Neuromechanical Model of Multiple Network Rhythmic Pattern Generators for Forward Locomotion in <i>C. elegans</i>.

Frontiers in computational neuroscience·2021
Same author

Persistent thermal input controls steering behavior in Caenorhabditis elegans.

PLoS computational biology·2021
Same author

Sources of predictive information in dynamical neural networks.

Scientific reports·2020

Related Experiment Video

Updated: Sep 25, 2025

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
10:44

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Published on: December 7, 2021

2.3K

Reinforcement Learning for Central Pattern Generation in Dynamical Recurrent Neural Networks.

Jason A Yoder1, Cooper B Anderson1, Cehong Wang1

  • 1Computer Science and Software Engineering Department, Rose-Hulman Institute of Technology, Terre Haute, IN, United States.

Frontiers in Computational Neuroscience
|April 25, 2022
PubMed
Summary

This study introduces a biologically inspired reinforcement learning mechanism for dynamic recurrent neural networks, enabling autonomous lifetime learning and demonstrating robust performance on a central pattern generation task.

Keywords:
CTRNNdynamic synapsedynamical neural networkslifetime learningneuromodulatory rewardreinforcement learning

More Related Videos

Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates
10:18

Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates

Published on: July 9, 2020

3.0K
Preparation of Rhythmically-active In Vitro Neonatal Rodent Brainstem-spinal Cord and Thin Slice
06:32

Preparation of Rhythmically-active In Vitro Neonatal Rodent Brainstem-spinal Cord and Thin Slice

Published on: March 23, 2019

11.8K

Related Experiment Videos

Last Updated: Sep 25, 2025

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
10:44

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Published on: December 7, 2021

2.3K
Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates
10:18

Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates

Published on: July 9, 2020

3.0K
Preparation of Rhythmically-active In Vitro Neonatal Rodent Brainstem-spinal Cord and Thin Slice
06:32

Preparation of Rhythmically-active In Vitro Neonatal Rodent Brainstem-spinal Cord and Thin Slice

Published on: March 23, 2019

11.8K

Area of Science:

  • Computational Neuroscience
  • Artificial Intelligence
  • Machine Learning

Background:

  • Lifetime learning is crucial for organisms, with biological neural circuits playing a key role.
  • Current models of dynamic recurrent neural networks (RNNs) often lack explicit lifetime learning rules, relying on evolutionary algorithms for behavior discovery.
  • Existing RNNs can exhibit learning but lack intrinsic mechanisms for real-time adaptation based on experience or reward signals.

Purpose of the Study:

  • To investigate a biologically plausible lifetime learning mechanism for dynamic recurrent neural networks.
  • To extend a well-established RNN model with a novel reinforcement learning mechanism inspired by neuromodulation.
  • To evaluate the effectiveness and efficiency of this new learning approach.

Main Methods:

  • Incorporated a reinforcement learning mechanism, inspired by neuromodulatory reward signals and synaptic plasticity, into a dynamic recurrent neural network.
  • Tested the extended model on a central pattern generation task.
  • Compared the learning mechanism's robustness and efficiency against random walk and hill-climbing baseline models.
  • Analyzed the impact of meta-parameters on learning performance.

Main Results:

  • The extended RNN model autonomously learned to perform the central pattern generation task.
  • The proposed reinforcement learning mechanism demonstrated superior robustness and efficiency compared to baseline methods.
  • Systematic analysis revealed the influence of meta-parameters on behavioral learning outcomes.
  • Preliminary findings suggest potential for generality and scalability in other dynamical neural network applications.

Conclusions:

  • The developed reinforcement learning mechanism provides a biologically plausible and effective method for enabling lifetime learning in dynamic recurrent neural networks.
  • This approach offers a significant advancement over traditional evolutionary methods for configuring RNNs.
  • Further research is warranted to explore the full potential and applications of this learning mechanism.