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...

You might also read

Related Articles

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

Sort by

Same author

Material damage to multielectrode arrays after electrolytic lesioning is insignificant.

eLife·2026

Same author

A mosaic of whole-body representations on the human precentral gyrus.

Nature·2026

Same author

Long-term independent use of an intracortical brain-computer interface for speech and cursor control.

Nature medicine·2026

Same author

Neural decoding of speech using deep neural ensembles.

bioRxiv : the preprint server for biology·2026

Same author

Targeted Connectomic Neuromodulation of the Orbitofrontal Cortex To Treat Obsessive-Compulsive Disorder.

medRxiv : the preprint server for health sciences·2026

Same author

Premotor cortex uses a compositional neural geometry to plan words.

bioRxiv : the preprint server for biology·2026

Same journal

A computational framework for fitting biophysical basal-ganglia network models, applied to Parkinsonian beta oscillations.

Journal of neural engineering·2026

Same journal

A sensor-driven Hill-type muscle modeling framework integrating sEMG and pFMG for biceps brachii force estimation.

Journal of neural engineering·2026

Same journal

Overcoming brain non-stationarity: Adaptive RLS classification for stable BCIs based on auditory evoked potentials.

Journal of neural engineering·2026

Same journal

Mapping neural representations of fine and gross upper-limb movements across dorsoventral subthalamic nucleus subregions in Parkinson's disease.

Journal of neural engineering·2026

Same journal

Ultra-flexible wireless endovascular stimulator for cortical simulation.

Journal of neural engineering·2026

Same journal

Influence of frequency and pulse train duration on respiratory responses during transcutaneous phrenic nerve stimulation in humans.

Journal of neural engineering·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 24, 2026

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

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

Published on: March 2, 2015

A recurrent neural network for closed-loop intracortical brain-machine interface decoders.

David Sussillo¹, Paul Nuyujukian, Joline M Fan

¹Department of Electrical Engineering, Stanford University, Stanford, CA 94305-9505, USA. sussillo@stanford.edu

Journal of Neural Engineering

|March 20, 2012

Summary

This summary is machine-generated.

This study introduces the FORCE decoder, a type of recurrent neural network (RNN), for brain-machine interfaces (BMIs). The FORCE decoder significantly outperforms traditional methods in decoding monkey reaches, offering more naturalistic cursor control.

More Related Videos

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

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

Published on: March 10, 2011

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Related Experiment Videos

Last Updated: May 24, 2026

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

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

Published on: March 2, 2015

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

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

Published on: March 10, 2011

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Area of Science:

Computational Neuroscience
Machine Learning
Neuroprosthetics

Background:

Recurrent neural networks (RNNs) excel at modeling complex temporal dependencies in time series data.
Brain-machine interfaces (BMIs) require robust decoders to translate neural signals into intended actions.
Existing decoding methods, like the velocity Kalman filter (VKF), have limitations in performance and naturalness.

Purpose of the Study:

To evaluate the efficacy of an echostate network (ESN) implementation, the FORCE decoder, for continuous decoding of monkey reaches in a closed-loop BMI.
To compare the FORCE decoder's performance against the state-of-the-art velocity Kalman filter (VKF).
To assess the FORCE decoder's robustness, generalizability, and the naturalness of decoded movements.

Main Methods:

Utilized a simplified RNN, an ESN termed the FORCE decoder, for decoding neural activity during a center-out reach task.
Implemented a closed-loop cortical brain-machine interface (BMI) system.
Compared the FORCE decoder against the velocity Kalman filter (VKF) using metrics like target acquisition time and success rate.

Main Results:

The FORCE decoder demonstrated rapid learning and significantly outperformed the VKF in target acquisition time.
The decoder successfully generalized to a more complex randomized point-to-point task and showed robustness over extended sessions.
Decoded cursor dynamics using the FORCE decoder more closely resembled naturalistic hand movements compared to the VKF.

Conclusions:

Recurrent neural networks, specifically the FORCE decoder, represent a powerful advancement for BMI decoder applications.
The FORCE decoder offers superior performance, robustness, and more naturalistic control compared to current state-of-the-art methods.
This approach holds significant promise for improving the functionality and user experience of brain-machine interfaces.