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

Hierarchy of Motor Control01:18

Hierarchy of Motor Control

3.3K
The hierarchy of motor control refers to the different levels of organization and processing involved in controlling movement in the body. These levels range from higher cortical areas involved in planning and decision-making to lower spinal cord reflexes that respond automatically to external stimuli.
3.3K
Neural Regulation01:37

Neural Regulation

39.7K
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.
39.7K
Neural Control of Respiration01:18

Neural Control of Respiration

2.8K
The neural regulation of respiration is a meticulously coordinated process primarily controlled by the respiratory centers located within the brainstem. These centers, composed of specialized neurons, transmit nerve impulses that control the contraction and relaxation of our respiratory muscles.
Respiratory Centers in the Brainstem
Two primary areas comprise the respiratory center: the medullary respiratory center in the medulla oblongata and the pontine respiratory group in the pons. The...
2.8K

You might also read

Related Articles

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

Sort by
Same author

Dendritic nonlinearities mitigate communication costs.

Patterns (New York, N.Y.)·2026
Same author

MPLIF: Multi-parametric leaky integrate-and-fire neuron for spiking neural networks.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Why Empirical Risk Minimization Performs Well for Open Set Domain Adaptation: A Theoretical Analysis From Causal View.

IEEE transactions on neural networks and learning systems·2026
Same author

Artificial plateau neurons with in-situ spike-malleability for rhythmic quadrupedal locomotion.

Nature communications·2026
Same author

Nonlinear Transformed Low-Rank Quaternion Tensor Total Variation for Multidimensional Color Image Completion.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

SFedCA: Credit Assignment-Based Active Client Selection Strategy for Spiking Federated Learning.

IEEE transactions on neural networks and learning systems·2025

Related Experiment Video

Updated: Aug 29, 2025

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.4K

Human-Level Control Through Directly Trained Deep Spiking Q-Networks.

Guisong Liu, Wenjie Deng, Xiurui Xie

    IEEE Transactions on Cybernetics
    |September 5, 2022
    PubMed
    Summary

    This study introduces a directly trained deep spiking Q-network (DSQN) for energy-efficient reinforcement learning. The proposed method achieves state-of-the-art performance on Atari games, outperforming existing techniques.

    More Related Videos

    Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments
    05:19

    Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments

    Published on: November 12, 2019

    7.1K
    An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
    10:51

    An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

    Published on: March 10, 2011

    13.8K

    Related Experiment Videos

    Last Updated: Aug 29, 2025

    Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
    11:18

    Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

    Published on: March 2, 2015

    10.4K
    Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments
    05:19

    Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments

    Published on: November 12, 2019

    7.1K
    An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
    10:51

    An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

    Published on: March 10, 2011

    13.8K

    Area of Science:

    • Artificial Intelligence
    • Computational Neuroscience
    • Machine Learning

    Background:

    • Spiking Neural Networks (SNNs) offer high energy efficiency for neuromorphic hardware.
    • Deep Spiking Reinforcement Learning (DSRL) faces challenges due to binary outputs and non-differentiable spiking functions.

    Purpose of the Study:

    • To propose a directly trained Deep Spiking Q-Network (DSQN) to overcome limitations in DSRL.
    • To enhance the performance, stability, generalization, and energy efficiency of DSRL.

    Main Methods:

    • Developed a DSRL architecture using Leaky Integrate-and-Fire (LIF) neurons and Deep Q-Network (DQN).
    • Adapted a direct spiking learning algorithm for the proposed DSQN.
    • Theoretically demonstrated the advantages of LIF neurons within the DSQN framework.

    Main Results:

    • Achieved state-of-the-art performance on 17 Atari games.
    • Demonstrated superior performance, stability, generalization, and energy efficiency compared to conversion-based methods.
    • Successfully trained an SNN directly for DSRL tasks.

    Conclusions:

    • The proposed DSQN offers a significant advancement in directly trained DSRL.
    • This work represents the first direct training of SNNs to achieve state-of-the-art results in multiple Atari games.
    • The findings highlight the potential of SNNs for efficient and high-performing reinforcement learning applications.